Diversity of fish sound types in the Pearl River Estuary, China

Acoustic data recording system

Underwater acoustic recordings were made using a Song Meter Marine Recorder (Wildlife Acoustics, Inc., Maynard, MA, USA), which included an HTI piezoelectric omnidirectional hydrophone (model HTI-96-MIN; High Tech, Inc., Long Beach, MS, USA) with a sensitivity of −164 dB re 1 V/µPa at 1 m distance, a recording bandwidth of 2 Hz–48 kHz and a flat frequency response over a wide range of 2 Hz–37 kHz (±3 dB). The hydrophone also included a programmable autonomous signal processing unit integrated with a band-pass filter and a pre-amplifier. The signal processing unit can log data at a resolution of 16 bits and at a 96 kHz sampling rate, with a storage capacity of 512 GB. The signal processing unit was sealed inside a waterproof PVC housing and was submersible to 150 m. The recording system was calibrated prior to shipment from the manufacturer.

Data collection

Static acoustic monitoring was conducted underwater at the base of a telephone signal tower (22°07′54″N, 113°43′54″E) located among the Sanjiao, Chitan and Datou islands (Fig. 1). The recordings were taken continuously throughout deployment periods from May 26 to June 4, 2014, and June 17 to 22, 2014, at a 96 kHz sampling rate. The acoustic recording system was attached to a steel wire rope and suspended below the signal tower in the middle of water column 4.0 m above the ocean floor and approximately 3.0–5.8 m (depending on the tide conditions) below the water surface. A 40 kg anchor block was attached on the bottom of the steel wire rope and laid down on the seabed to reduce the movement of the recording system due to water currents.

Acoustic data analysis

Upon retrieval of the recorder, the acoustic data were downloaded and processed. Raven Pro Bioacoustics Software (version 1.4; Cornell Laboratory of Ornithology, NY, USA) was used to initially visualize the acoustic data in the spectrogram (window type: Hann windows; fast Fourier transform (FFT) size: 2048 samples; frame overlapping: 80%; frequency grid spacing: 46.88 Hz; temporal grid resolution: 4.26 ms). Only calls with good signal-to-noise ratios (SNR >15 dB, noise level obtained just before or after the pulse) and satisfying the criteria of no interference by other sounds were extracted for further quantitative analyses. To make the data more independent and reduce the possibility of using multiple sounds from the same individual, only one signal was extracted for each call type in every 10 min bin for further analysis.

The recorded sounds generally featured single or multiple-pulse structures. A custom acoustic analysis routine based on MATLAB 7.11.0 (The Mathworks, Natick, MA, USA) was developed to analyze the extracted calls. For each call, the peak amplitude time for each pulse within the call was logged using a pulse-peak detector. Through trial and error, the pulse was defined and extracted as an 8 ms signal that began 2.5 ms before and ended 5.5 ms after the time point of the peak amplitude (Figs. 2B and 2C). The 8 ms definition was validated because it encompassed the majority of the energy of a pulse and was longer than the shortest interval between pulses within a call. The sonic parameters of the number of pulses in a call, total call duration (in ms), inter-pulsepeak interval (IPPI), and the inter-pulse interval (IPI) were calculated for each call. Call duration is derived by adding 8 ms to the time difference of the last pulsepeak and the first pulsepeak; IPPI is the time difference between the peak amplitude of consecutive pulse units in the train, which is equal to the pulse period in the literature (Parmentier et al., 2009), and IPI is the time interval between the end of one pulse and the onset of the next one in a series. The temporal characteristics for each 8 ms pulse were computed as τ_95%, τ_−3dB and τ_−10dB.τ_95% is the duration containing 95% of the cumulative energy of the pulse (Fig. 2D), which began when 2.5% of the cumulative signal energy was reached (CE_2.5% in Fig. 2D) and ended when 97.5% of the cumulative signal energy was reached (CE_97.5% in Fig. 2D), and τ_−3dB and τ_−10dB are the time differences between the end points that were 3 dB and 10 dB lower than the peak amplitude of the envelope of the pulse waveform, respectively (Fig. 2E). The signal envelope was generated by taking the absolute value of the waveform after applying the Hilbert transform function (Au, 1993; Madsen & Wahlberg, 2007). The frequency and bandwidth properties for each 8 ms pulse were determined from the power spectrum, which was calculated from the squared fast Fourier transform of a 96,000-point Hanning window. Parameters of the peak frequency (f_p, the frequency at which the spectrum has its maximum value) (Fig. 2F), center frequency (f_c, the frequency that divides the power spectrum into equal energy halves) and centralized root-mean-square bandwidth (BW_rms, the spectral standard deviation of the f_c of the spectrum) (Au, 1993; Madsen & Wahlberg, 2007) were measured since they were proposed to be good descriptive parameters for signals with bimodal spectra (Au, 2004). Parameters of 3-dB and 10-dB bandwidths were not measured since they might only cover the frequency range near the peak frequency and tend to provide a misrepresentation of the bandwidth of signals with bimodal spectra (Au, 2004). The quality factor of each pulse (Q, an appropriate way to define the relative width of a signal) was computed as the ratio of the f_c to the BW_rms (Au, 1993; Au, 2004). The sound pressure levels (SPLs, dB re 1 µPa) and energy flux density (EFD, dB re 1 µPa²s) were derived for each 8 ms pulse over its τ_95%. The SPL parameters included the zero-to-peak SPL (SPL_zp) and the root-mean-square SPL (SPL_rms) (Urick, 1983). The absolute pressure levels were derived by subtracting the sensitivity of the hydrophone and the gain due to the amplifier (Urick, 1983).

The pooled distribution pattern of the IPPI for all analyzed calls was characterized by a multi-peak mode, with a distribution curve peaking at 9, 10, 12, 13 and 18 ms (Fig. 3A). Previous experience in fish acoustic analysis by other investigators indicated that the IPPI was the most reliable basis for signal identification and species-specific recognition (Mann & Lobel, 1997; Parmentier et al., 2009; Spanier, 1979), and most signals in our database ended with a pulse train featuring regular IPPIs (Table 1). In this study, calls were classified into types primarily based on their IPPI patterns and their amplitude and temporal modulation patterns (Table 1). The calls were initially grouped according to the number of sections they contained (Table 1). For each call, pulses with IPPIs greater than 1.5 times the median IPPI of the call were divided into different sections. Based on the bimodal distribution of the IPPI for calls that consisted of fewer than three pulses, pulses with an IPPI greater than 24 ms (three times the duration of a single pulse of 8 ms) were divided into different sections (Fig. 3B). To name each call type, such as 2 + 1 + N₁₀, (1 − )⁴ + (2 − )² + N₁₀ and ⁱN₁₃ (Figs. 4–6, Figs. S1–S26), ‘+’ was used to separate the different sections of a call, a number was used to denote the number of pulse for that section and ‘(1 −)’ and ‘(2−)’ to denote repeated sections that consist of one or two pulses, respectively, with digital superscripts denoting the number of repeats in a repeating section. ‘N’ was used to denote the last section of a call with a variable number of pulses, and the digital subscripts denote the median IPPIs of the last portion of the call; the subscript i was used to denote calls with a zero-to-peak sound pressure level of the first pulse approximately 10 dB weaker than that of the remainder of the call. Occasionally, a train of calls was extracted with significantly higher SNR (SNR > 25 dB), a regular inter-call interval, and a gradually changing pattern in its sound pressure level distinct from the ambient biological sounds. These sounds were likely produced by the same individual fish, which facilitated the estimation of the inter-call intervals.

Statistical analysis

Descriptive statistics were used to summarize the biographical information. All the parameters were tested for normality (using the Shapiro–Wilk test for data sets <50 or the Kolmogorov–Smirnov test for data sets ≥50) and homoscedasticity (using Levene’s test for equality of variance) (Zar, 1999). Because of the grossly skewed distribution of the majority of the data, the descriptive parameters of median, quartile deviation (QD), 5th percentile (P5), and 95th percentile (P95) were adopted. The QD was defined as one-half the interquartile range, which is the difference between the 25th and 75th percentiles in a frequency distribution.

Principal component analysis was used to identify the variables explaining the most variance among the acoustic parameters. Call types with an analyzed number greater than five were extracted for further discriminant and cluster analyses. Canonical discriminant analysis was used to assess the variation among call types relative to the variation within call types and determine the validity of our call types. Hierarchical cluster analysis (Romesburg, 2004), a step-wise process that merges the two closest or furthest data points at each step and builds a hierarchy of clusters based on the distance between them, was applied to discover similar call types in each set. Because the amplitude parameters were not critical for species recognition (Ha, 1973) and the call duration was dependent on the number of pulses in a call (Parmentier et al., 2009), these parameters were not included in the principal component analysis, canonical discriminant analysis and hierarchical cluster analysis. The statistical analyses were performed using Statistical Package for the Social Sciences 16.0 for Windows (SPSS Inc., Chicago, IL, USA).

Single-section calls

Calls that consisted of a single section included call types 1, 2 (Table S1, Fig. S1), N₉, N₁₀, N₁₃, N₁₇ (Table 2, Fig. 4), ⁱN₁₃ and ⁱN₁₅ (Table 3, Fig. 5).

Two-section calls

Calls consisting of two sections included call types 1 + 1 (Table S1, Fig. S1), 1 + N₁₀, 1 + N₁₂, 1 + N₁₉ (Table 4, Fig. 6), 2 + N₉, 2 + N₁₀, 2 + N₁₈ (Table S2, Fig. 7 and Fig. S2), 3 + N₉, 3 + N₁₀, 3 + N₁₇ (Table S3, Fig. 7 and Fig. S3), 4 + N₉, 4 + N₁₀, 4 + N₁₇ (Table S4, Fig. 7 and Fig. S4), and 5 + N₁₀ (Table S5, Fig. S5).

Three-section calls

Calls consisting of three sections included call types (1 − )² + N₉, (1 − )² + N₁₀, (1 − )² + N₁₂ (Table S6, Fig. 8 and Fig. S6), 1 + 2 + N₁₀, 1 + 2 + N₁₈ (Table S7, Fig. S7), 2 + 1 + N₉, 2 + 1 + N₁₀ (Table S8, Fig. S8), (2 − )² + N₁₀ (Table S9, Fig. S9), 3 + 1 + N₉, 3 + 1 + N₁₀ (Table S10, Fig. S10), 3 + 2 + N₉ (Table S11, Fig. S11) and 4 + 1 + N₁₀ (Table S9, Fig. S9).

Four-section calls

Calls consisting of four sections included call types (1 − )³ + N₉, (1 − )³ + N₁₀, (1 − )³ + N₁₂ (Table S12, Fig. 8 and Fig. S12), (1 − )² + 2 + N₉, (1 − )² + 2 + N₁₀ (Table S13, Fig. S13), (1 − )² + 3 + N₁₀ (Table S14, Fig. S14), 2 + (1 − )² + N₉, 2 + (1 − )² + N₁₀ (Table S15, Fig. S15), 2 + 1 + 2 + N₉, 2 + 1 + 2 + N₁₀ (Table S16, Fig. S16) and 3 + (1 − )² + N₉ (Table S11, Fig. S11).

Five-section calls

Calls consisting of five sections included call types (1 − )⁴ + N₉, (1 − )⁴ + N₁₀, (1 − )⁴ + N₁₂ (Table S17, Fig. 8C and Fig. S17), (1 − )³ + 2 + N₁₀, (1 − )³ + 3 + N₁₀ (Table S18, Fig. S18), (1 − )² + 2 + 1 + N₁₀, (1 − )² + 2 + 3 + N₁₀ (Table S19, Fig. S19), and 2 + (1 − )³ + N₁₀ (Table S20, Fig. S20).

Six-section calls

Calls consisting of six sections included call types (1 − )⁵ + N₉, (1 − )⁵ + N₁₀ (Table S21, Fig. 8 and Fig. S21), (1 − )⁴ + 2 + N₁₀, (1 − )⁴ + 3 + N₁₁ (Table S22 and Fig. S22), (1 − )³ + 2 + 1 + N₁₀ (Table S23 and Fig. S23), and 2 + (1 − )⁴ + N₁₀ (Table S20, Fig. S20).

Seven-section calls

Calls consisting of seven sections included call types (1 − )⁶ + N₁₀ (Table S24, Fig. 8H and Fig. S24), (1 − )⁵ + 2 + N₁₀, (1 − )⁵ + 3 + N₁₀ (Table S25 and Fig. S25), (1 − )⁴ + 2 + 1 + N₁₀ (Table S23 and Fig. S23), and (1 − )⁴ + (2 − )² + N₁₀ (Table S26 and Fig. S24).

Eight-section calls

Calls consisting of eight sections included call types (1 − )⁷ + N₁₀ (Table S24, Fig. 8I and Fig. S24) and (1 − )⁵ + (2 − )² + N₁₀ (Table S26 and Fig. S26).

Principal component, discriminant function and hierarchical cluster analyses

The principal component analysis indicated that approximately 81.1% of the variability is explained by the first four principal components (39.2% by principal component 1, 18.1% by principal component 2, 13.2% by principal component 3, and 10.6% by principal component 4). Principal component 1 was loaded with the τ_−3 dB, τ_−10 dB, f_c, BW_rms and Q parameters. Principal component 2 was loaded with f_p. The third component describes the temporal parameter of the IPPI, and the fourth component describes the temporal parameters of τ_−10 dB and the IPPI. The validity of our call types was confirmed using a canonical discriminant function that grouped N₁₇, 1 + N₁₉, 2 + N₁₈ and 3 + N₁₇ (Fig. 9A). Call types with an analyzed number greater than five were extracted for further discriminant and cluster analyses and 31 call types meet the requiment and account for 93.82% of all analyzed calls (Fig. S27). Hierarchical clustering using a between-groups linkage method that measures the squared Euclidean distance automatically grouped the 31 extracted call types into five clusters. The N₁₇, 1 + N₁₉, 2 + N₁₈ and 3 + N₁₇ call types were grouped into one cluster, and ⁱN₁₃ and ⁱN₁₅ were grouped together (Fig. 9B). Most of the call types with an IPPI median of 10 ms were grouped together, and those with an IPPI median of 9 ms were grouped together (Fig. 9B).

Call occurrence patterns

Almost all call types with median IPPIs of 9 ms for the last section (i.e., call types with median IPPIs of 9 ms except the N₉ call type) were only observed from June 18 to 20, 2014 (Fig. 10). Most of the call types with median IPPIs of 10 ms for the last section (88%, 29 out of 33), except 1 + N₁₀, (1 − )² + N₁₀, 1 + 2 + N₁₀, and (1 − )³ + N₁₀, were only observed from May 26 to June 4 and June 21 to 22, 2014 (Fig. 10).

Characteristics of call trains

Of the 52 extracted call trains, the estimated inter-call interval was 1.88 ± 0.39 ms (median ± QD; P5–P95: 1.05–3.04 ms, n = 278).

Sound comparison of soniferous fish in the PRE

The South China Sea, with at least 2,321 fish species belonging to 35 orders, 236 families and 822 genera (Ma et al., 2008), has long been recognized as a global center of marine tropical biodiversity (Barber et al., 2000) and is one of the richest areas in China, even globally, in terms of its marine fish diversity (Huang, 1994; Ma et al., 2008). More than 834 fish species belonging to 25 orders, 124 families and 390 genera were recorded in the waters near Hong Kong (Ni & Kwok, 1999).

Comparisons with Sciaenid sounds

Fishes of the family Sciaenidae, which are commonly known as croakers or drums, are some of the most well-studied soniferous fish species, and more than 23 species in this family were recorded in the waters near Hong Kong (Ni & Kwok, 1999).

Voluntary sounds

In free-ranging conditions, big-snout croaker (J. macrorhynus) can emit voluntary purr signals with the first and the remaining IPPIs averaging 40.1 ms and 9.7 ms in the field and 35.3 ms and 10.4 ms in a large aquarium, respectively (Table 5) (Lin, Mok & Huang, 2007), which resembles the 1 + N₁₀ call type in our study (Table 4, Fig. 6A) (note that the IPPI was equal to the summation of the pulse duration and the inter-pulse interval in Lin, Mok & Huang, 2007). In addition, the peak frequency of the pulses in 1 + N₁₀ (mean ± sd: 1,077 ± 244, N = 1,507) was intermediate between those in the pulses of big-snout croaker purr signals as recorded in the field (mean ± sd: 1,146 ± 131, N = 250) and in a large aquarium (mean ± sd: 1,050 ± 84, N = 60). Additionally, the voluntary dual-knock signal of big-snout croaker with an average IPPI of 36.7 ms and 39.4 ms as recorded in the field and in a large aquarium, respectively (Table 5) (Lin, Mok & Huang, 2007), resembled the 1 + 1 call type in our study with an IPPI of 40.70 ± 4.08 (mean ± sd) (Table S1, Fig. S1B). These matches were further supported by the fact that the peak frequency of the pulses in the 1 + 1 call type (mean ± sd: 1077.75 ± 219.58, N = 126) was close to that of the dual-knock recorded in the field (mean ± sd: 1,133 ± 119, N = 40) or a large aquarium (mean ± sd: 1,135 ± 85, N = 50).

It is possible that J. macrorhynchus might emit dual-knock and purr signals in series and creates a multiple section call type, such as one dual knock combined with one purr which may result in a synthetic three section call type of 1 + 2 + N₁₀ (time gap between the two signals was equal to 10 ms) or a four section call type of 1 + 1 + 1 + N₁₀ (time gap between the two signals was over 20 ms). However, both of the synthetic 1 + 2 + N₁₀ and 1 + 1 + 1 + N₁₀ signals with the third IPPI ascribed to the first IPPI of the purr signal and averaged at 40.1ms (Lin, Mok & Huang, 2007) cannot match either the 1 + 2 + N₁₀ or the 1 + 1 + 1 + N₁₀ call types in our study, since both of which with the third IPPI of less than 30 ms (Fig. S7A and Fig. S12B). Belanger’s croaker can emit sounds with the first IPPI much longer than subsequent IPPIs, which follow at regular intervals of approximately 20 ms (Pilleri, Kraus & Gihr, 1982) and resemble the 1 + N₁₉ call type in our study, although the first IPPI in Belanger’s croaker (approximately 40 ms) (Table 5) (Pilleri, Kraus & Gihr, 1982) was smaller than that in the 1 + N₁₉ call type (median at 71.36 ms) (Table 4, Fig. 6C). Their similarity was further strengthened by the fact that the temporal and frequency characteristics of the signal emitted by Belanger’s croaker, which consists of 4–14 pulses with a 140–260 ms call duration, a 500–1,000 Hz peak frequency and a majority of the energy within the 500–4,000 Hz frequency band (Pilleri, Kraus & Gihr, 1982), resemble those of the 1 + N₁₉ call type, which consists of 3–12 pulses with a 97.37–272.85 ms call duration and peak frequency median of approximately 789 Hz (Table 4).

Sounds from the white croaker (Pennahia argentata) (Ramcharitar, Gannon & Popper, 2006; Takemura, Takita & Mizue, 1978), southern meagre (Argyrosomus japonicus) (Ueng, Huang & Mok, 2007), yellow drum (Nibea albiflora) (Ramcharitar, Gannon & Popper, 2006; Ren et al., 2007; Takemura, Takita & Mizue, 1978), Reeve’s croaker (N. acuta or Chrysochir aureus) (Ren et al., 2007; Trewavas, 1971) and large yellow croaker (Liu, Xu & Qin, 2010; Ren et al., 2007) were also compared. However, these sounds (Table 5) did not match any call types in our study based on their temporal and/or frequency characteristics.

Belanger’s croaker can also emit long bursts with a peak frequency of 750–1,250 Hz (Pilleri, Kraus & Gihr, 1982), and a chorus sound of unknown species recorded in Xiamen Harbor of East China Sea from 1981 to 1982 with sound energy concentrated in the 700–1,600 Hz frequency band and a peak frequency of 1,250 Hz was proposed to be emitted by Belanger’s croaker (Zhang et al., 1984). Chorus sounds of the genus Johnius (possibly J. fasciatus or J. amblycephalus) and the genus Pennahia (possibly P. miichthioides) recorded in the Bohai Sea and Yellow Sea from 1989–1990 were also reported. The sounds emitted by the former genus have an average peak frequency of 2,000 Hz and a majority of energy concentrated in the 1,000–4,000 Hz frequency band, whereas the sounds emitted by the latter genus have an average peak frequency of 400 Hz and majority of energy concentrated in the 200–800 Hz frequency band (Xu & Qi, 1999). Chorus sounds of the spiny-head croaker were recorded in the South China Sea, with a majority of energy concentrated in the 500–1,250 Hz frequency band and a peak frequency of approximately 1,000 Hz (Qi, Zhang & Song, 1982). Chorus sounds of unknown species recorded in the adjacent waters of Xiamen Harbor of the East China Sea from 1981 to 1982, with sound energy concentrated in the 700–1,600 Hz frequency band and peak frequencies of 800 Hz and 1,000 Hz, were ascribed to the spiny-head croaker (Zhang et al., 1984). However, detailed waveform, spectrum and statistical results for the temporal and frequency characteristics of individual sounds in these choruses were not available, preventing direct comparison with our study.

Disturbance sound

Sound recorded under disturbance, e.g., under hand-held conditions is possibly not significantly different from those recorded under voluntary conditions and can be employed to match the sound in the field (Lin, Mok & Huang, 2007). In addition, the sound recording region is a hot spot of humpback dolphin (Wang et al., 2015b), the predator of soniferous fish, which may impose a stress for local fish and may trigger them to emit signal similar to the hand-held disturbance call. Thus, we also compared the disturbance sound of the sciaenid species distributed in our study region, including Belanger’s croaker (Mok, Lin & Tsai, 2011), big-snout croaker (Huang, 2016; Lin, Mok & Huang, 2007; Mok, Lin & Tsai, 2011), J. distincus, J.amblycephalus and J. sp., sin croaker (J. dussumieri), white croaker, greyfin croaker, bighead white croaker (P. macrocephalus), pawak croaker (P. pawak), Reeve’s croaker, tiger-toothed croaker (Otolithes ruber), and blackmouth croaker (Atrobucca nibe) (Huang, 2016; Mok, Lin & Tsai, 2011; Tsai, 2009). However, the temporal and frequency patterns of these signals did not match any call types in our study (Table 5).

Comparison with other soniferous fish families

Sounds from other soniferous fish families, including cutlassfish (Trichiurus haumela, family: Trichiuridae), elongate ilisha (Ilisha elongata, family: Pristigasteridae) (Ren et al., 2007), sea catfish (Arius sp. and A. maculates, family: Ariidae) (Mok, Lin & Tsai, 2011; Ren et al., 2007), pearl perch (Glaucosoma buergeri, family: Glaucosomatidae) (Mok et al., 2011), bigeye snapper (Priacanthus macracanthus, family: Priacanthidae), trumpeter perch (Pelates quadrilineatus, family: Terapontidae) and javelin grunter (Pomadasys kaakan, family: Haemulidae) (Tsai, 2009) were also compared with our call types but did not match any call types in our study in the temporal and spectral characteristics (Table 5).

Comparison with biological sounds from other passive acoustic monitoring sites

The statistical parameters of the eight types of wild fish sounds recorded in seven estuaries of the west coast of Taiwan using passive acoustics were unfortunately not available, which restricted direct comparison (Mok, Lin & Tsai, 2011). However, the general trend of the 1 + N₁₀ and 1 + N₁₂ call types in our study resembles their type B signal (Mok, Lin & Tsai, 2011), with the first inter-pulse interval much longer than the following ones that had a non-increasing inter-pulse interval toward the end of the call, and the N₁₇ call type in our study resembles their type E signal (Mok, Lin & Tsai, 2011), with a gradually increasing inter-pulse interval toward the end of the call and the sound energy concentrated in discrete bands. Sounds with much longer second or third inter-pulse intervals, which resemble our 2 + N and 3 + N, respectively, were also observed in the Chosui River in Taiwan (Mok, Lin & Tsai, 2011), but the sound producer was not identified. Four call types from three recording sites on the northwestern coast of Taiwan were recorded, with the call type identical to the purr signal of J. macrorhynus dominated the soundscape and was the most abundance call type of these sites (Huang, 2016). The waveform of call type T3 resemble our call types of ⁱN₁₃ and ⁱN₁₃ (Huang, 2016).

Occurrence pattern of call types

In the field environment, to communicate without misinterpreting messages and to avoid jamming, different species of a fish community will partition the underwater acoustic environment (Ruppé et al., 2015). In our study, most call types with IPPI medians at 9 ms and 10 ms were observed at times that were exclusive from each other, suggesting they might have been produced by different species.

The spotted seatrout (Cynoscion nebulosus) is one of the few sciaenid species that produces as many as four types of call (Mok & Gilmore, 1983). It is likely that most sciaenid species have fewer call types. Of all the 66 call types recognized in the survey sites, some of the which might come from the same species. According to the result of cluster analysis, five clades were revealed. However, it is still too early to hypothesize that these groups belong to the call repertoire of five species. Additional studies with more controlled conditions, such as in an aquarium or with field recording equipped with a high-definition sonar system such as the DIDSON Dual-frequency Identification Sonar system, will be required to identify the species producing the calls in our study.

Call trains

Due to the relative simplicity of vocal mechanisms and lack of ability to produce complex calls, fish typically emit sounds with variation in either the temporal and/or frequency patterning (Rice & Bass, 2009). As most of the call types were identified based on the number of sections and the repetition of the anterior section, it is likely that a species might be able to produce several call types by varying the anterior sections of the call as a response to the variable external stimuli. Additionally, the temporal and spectral characteristics of fish signals are involved in information coding and are important parameters for the recognition of sound in fishes (Malavasi, Collatuzzo & Torricelli, 2008; Spanier, 1979). In the present study, fish sounds tended to be frequency modulated, e.g., the peak frequency of the pulses within a call were variable (Fig. 2F), and amplitude modulated, e.g., the ⁱN₁₃ and ⁱN₁₅ call types. This is possible because the amplitude of the sound is determined by the swim bladder (Fine et al., 2001; Tavolga, 1964) and the dominant frequency of the signal is determined by the sonic muscle twitch duration and the forced response of the swim bladder to sonic muscle contractions rather than the natural resonant frequency of the swim bladder (Connaughton, Fine & Taylor, 2002). Additionally, the length of the sonic muscle fibers also related to the body size of the fish (Parmentier & Fine, 2016).

Passive hearing by the dolphin

The Pearl River Estuary shelters the world’s largest known population of Indo-Pacific humpback dolphins (Chen et al., 2010; Jefferson & Smith, 2016; Preen, 2004), with an estimated population of 2,637 (Coefficient of variation of 19% to 89%) (Chen et al., 2010; Jefferson & Smith, 2016). The general preference of this species for estuarine habitats and coastal and shallow water (<30 m depth) distribution make it susceptible to the impacts of human activity (Jefferson & Smith, 2016). The current conservation status of the Chinese white dolphin meets the IUCN Red List criteria for classification as Vulnerable; however, the conservation management in a majority of its distribution range is severely inadequate, and the humpback dolphin population in the Pearl River Estuary is declining by 2.5% annually (Karczmarski et al., 2016).

The humpback dolphin appears to rely almost exclusively on fish for food (Barros, Jefferson & Parsons, 2004; Parra & Jedensjö, 2014). Its prey includes the fish families of Sciaenidae (croakers), Engraulidae (anchovies), Trichiuridae (cutlassfish), Clupeidae (sardines), Ariidae (sea catfish) and Mugilidae (mullets) (Barros, Jefferson & Parsons, 2004; Parra & Jedensjö, 2014). Notably, the majority of these species are soniferous fishes (Banner, 1972; Fish & Mowbray, 1970; Ren et al., 2007; Whitehead & Blaxter, 1989). The top three most important and frequent prey of humpback dolphins in the Pearl River Estuary are the brackish water species of croaker (Johnius sp.), spiny-head croaker (C. lucidus), and anchovies (Thryssa spp., T. dussumieri and/or T. kammalensis) (Barros, Jefferson & Parsons, 2004). The former two are soniferous fishes (Ren et al., 2007), and the latter might be capable of making sounds (Whitehead & Blaxter, 1989). Additionally, it has been proposed that dolphins rely heavily on eavesdropping (passive listening) (Barros, 1993; De Oliveira Santos et al., 2002) during the search phase of the foraging process (Gannon et al., 2005).

In addition to emitting high-frequency pulsed sounds for echolocation and navigation, humpback dolphins can produce narrow-band, frequency-modulated whistles with a fundamental frequency range of 520–33,000 Hz (Wang et al., 2013) and apparent source levels of 137.4 ± 6.9 dB re 1 µPa in rms (Wang et al., 2016) for communication. The fish sounds recorded in this study, which were characterized by a peak frequency between 500 and 2,600 Hz and a maximum zero-to-peak sound pressure level greater than 164 dB, were well within the frequency range of humpback dolphin whistles. It is highly probable that the fish sounds function as acoustic clues of prey to the dolphin, i.e., the dolphin relies heavily on passive hearing during the search phase of the foraging process. On the other hand, the brackish water species of C. lucidus and tapertail anchovy (Coilia mystus, Family: Engraulidae) were the top two predominant species in the seawater/freshwater mixing zones of the Pearl River Estuary (Zhan, 1998), accounting for 89% and 72% of the numbers and biomass, respectively, of the whole fish stock in the Pearl River Estuary region (Wang & Lin, 2006). While, the soniferous fish C. lucidus was observed to be the second-most important prey for humpback dolphin, but the non-soniferous fish C. mystus was not identified in their prey spectrum (Barros, Jefferson & Parsons, 2004). This fact can further reinforce the passive hearing mechanism of the local humpback dolphin.

Importance and application

The high biodiversity of fish fauna dwell at the Pearl River Estuary is a treasure of genetic resources and has great potential application value. However, the loss of the fishery stocks over time has been devastating. Historically poor management and overfishing of wild stocks of the large yellow croaker resulted in overwhelming collapses throughout its geographic range (Liu & Sadovy, 2008), and although substantial funds have been provided and many remedial actions such as fishery control, restocking and marine aquaculture have been applied. However, aquaculture can only supplement, rather than substitute, wild fisheries (Goldburg & Naylor, 2005). No evidence of recovery in the wild stock of large yellow croaker has been observed, and its genetic diversity continues to decrease (Liu & Sadovy, 2008). Similar lessons can be learned from the Atlantic salmon (Salmo salar) (Goldburg & Naylor, 2005). Given the sharp declines in fish stocks, especially of the larger species of croakers owing to overfishing in the Pearl River Estuary, and given that fishing pressure is still high and may be even higher in the future, management activities such as more effective fishing moratoriums should be applied to protect the remaining croakers and other fisheries during the spawning season, especially at their spawning grounds. The baseline data of the ambient biological acoustics in our study represent a first step toward mapping the spatial and temporal patterns of soniferous fishes and are helpful for the protection, management and effective utilization of fishery resources. In addition, since marine environmental impact assessment must be based upon a good understanding of the local biodiversity, the baseline data of suspected fish sounds in our study can facilitate the evaluation of the impacts from various infrastructure projects on local aquatic environments by comparing the baseline to post-construction and/or post-mitigation effort data. Additionally, there is a large body of evidence that the distribution pattern of marine mammals tends to be correlated with the spatial–temporal variability of their prey (Benoit-Bird & Au, 2003; Wang et al., 2015a; Wang et al., 2014a); this correlation was also proposed for the vulnerable local humpback dolphin (Wang et al., 2015b), and the fine-scale distribution pattern of soniferous fishes can aid in the conservation of these emblematic dolphins.