GWA: A Large High-Quality Acoustic Dataset for Audio Processing

Tang, Zhenyu; Aralikatti, Rohith; Ratnarajah, Anton; Manocha, Dinesh

doi:10.1145/3528233.3530731

Cited by 8 publications

(3 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We use word error rate (WER) to evaluate the performance of the ASR system. Lower WER indicates that the reverberation effects in the training speech data are closer to the test speech data (SDM) [10]. From Table 3, we can see that our S2IR-GAN outperforms FiNS by 6.9%.…”

Section: Asr Evaluationmentioning

confidence: 88%

“…Accurate measurement of RIRs is prohibitively expensive and requires expert guidance [2]. On the other hand, simulating accurate RIRs requires 3D mesh representations of the underlying scenes [8] and complete knowledge of material properties [9,10]. Therefore, it is not practical to precisely simulate RIRs for a real-world environment without their 3D representation.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

IR-GAN: Room Impulse Response Generator for Far-Field Speech Recognition

Ratnarajah¹,

Tang

Manocha

2021

Interspeech 2021

View full text Add to dashboard Cite

We present a Generative Adversarial Network (GAN) based room impulse response generator for generating realistic synthetic room impulse responses. Our proposed generator can create synthetic room impulse responses by parametrically controlling the acoustic features captured in real-world room impulse responses. Our GAN-based room impulse response generator (IR-GAN) is capable of improving far-field automatic speech recognition in environments not known during training. We create far-field speech training set by augmenting our synthesized room impulse responses with clean Lib-riSpeech dataset [1]. We evaluate the quality of our room impulse responses on the real-world LibriSpeech test set created using real impulse responses from BUT ReverbDB [2] and AIR [3] datasets. Furthermore, we combine our synthetic data with synthetic impulse responses generated using acoustic simulators, and this combination can reduce the word error rate by up to 14.3% in far-field speech recognition benchmarks.

show abstract

Section: Asr Evaluationmentioning

confidence: 88%

Section: Introductionmentioning

confidence: 99%

IR-GAN: Room Impulse Response Generator for Far-Field Speech Recognition

Ratnarajah¹,

Tang

Manocha

2021

Interspeech 2021

View full text Add to dashboard Cite

show abstract

“…In computational room modeling, in which low frequencies are handled using the wave principle whereas high-frequency modeling uses the ray-tracing principles, a crossover network can help combine the low and high frequencies [178,179]. In another room modeling application by Ouellet et al, the frequency-dependent properties of acoustic propagation and absorption vary for each octave band, and the band-splitting is implemented using a Linkwitz-Riley filterbank [180].…”

Section: Other Applications Of Crossover Filtersmentioning

confidence: 99%

Crossover Networks: A Review

Cecchi,

Bruschi,

Nobili

et al. 2023

J. Audio Eng. Soc.

View full text Add to dashboard Cite

Crossover networks for multi-way loudspeaker systems and audio processing are reviewed, including both analog and digital designs. A high-quality crossover network must maintain a flat overall magnitude response, within small tolerances, and a sufficiently linear phase response. Simultaneously, the crossover filters for each band must provide a steep transition to properly separate the bands, also accounting for the frequency ranges of the drivers. Furthermore, crossover filters affect the polar response of the loudspeaker, which should vary smoothly and symmetrically in the listening window. The crossover filters should additionally be economical to implement and not cause much latency. Perceptual aspects and the inclusion of equalization in the crossover network are discussed. Various applications of crossover filters in audio engineering are explained, such as in multiband compressors and in effects processing. Several methods are compared in terms of the basic requirements and computational cost. The results lead to the recommendation of an all-pass-filter-based Linkwitz-Riley crossover network, when a computationally efficient minimum-phase solution is desired. When a linear-phase crossover network is selected, the throughput delay becomes larger than with minimum-phase filters. Digital linear-phase crossover filters having a finite impulse response may be designed by optimization and implemented efficiently using a complementary structure.

show abstract

Evaluation of SSIM loss function in RIR generator GANs

Pekmezci,

Genc

2024

Digital Signal Processing

View full text Add to dashboard Cite

GWA: A Large High-Quality Acoustic Dataset for Audio Processing

Cited by 8 publications

References 41 publications

IR-GAN: Room Impulse Response Generator for Far-Field Speech Recognition

IR-GAN: Room Impulse Response Generator for Far-Field Speech Recognition

Crossover Networks: A Review

Evaluation of SSIM loss function in RIR generator GANs

Contact Info

Product

Resources

About