TS-RIR: Translated synthetic room impulse responses for speech augmentation
| Autor: | Ratnarajah, Anton, Tang, Zhenyu, Manocha, Dinesh |
|---|---|
| Rok vydání: | 2021 |
| Předmět: | |
| DOI: | 10.48550/arxiv.2103.16804 |
| Popis: | We present a method for improving the quality of synthetic room impulse responses for far-field speech recognition. We bridge the gap between the fidelity of synthetic room impulse responses (RIRs) and the real room impulse responses using our novel, TS-RIRGAN architecture. Given a synthetic RIR in the form of raw audio, we use TS-RIRGAN to translate it into a real RIR. We also perform real-world sub-band room equalization on the translated synthetic RIR. Our overall approach improves the quality of synthetic RIRs by compensating low-frequency wave effects, similar to those in real RIRs. We evaluate the performance of improved synthetic RIRs on a far-field speech dataset augmented by convolving the LibriSpeech clean speech dataset [1] with RIRs and adding background noise. We show that far-field speech augmented using our improved synthetic RIRs reduces the word error rate by up to 19.9% in Kaldi far-field automatic speech recognition benchmark [2]. Comment: Accepted to IEEE ASRU 2021. Source code is available at https://github.com/GAMMA-UMD/TS-RIR |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|