Towards Improved Room Impulse Response Estimation for Speech Recognition
Abstract: We propose to characterize and improve the performance of blind room impulse response (RIR) estimation systems in the context of a downstream application scenario, far-field automatic speech recognition (ASR). We first draw the connection between improved RIR estimation and improved ASR performance, as a means of evaluating neural RIR estimators. We then propose a GAN-based architecture that encodes RIR features from reverberant speech and constructs an RIR from the encoded features, and uses a novel energy decay relief loss to optimize for capturing energy-based properties of the input reverberant speech. We show that our model outperforms the state-of-the-art baselines on acoustic benchmarks (by 72% on the energy decay relief and 22% on the early reflection energy metrics), as well as in an ASR evaluation task (by 6.9% in word error rate).
Github
Our github code is available here https://github.com/anton-jeran/Speech2RIR/Audio Demos
| Clean Speech | Ground truth RIR | Input reverberant speech | Estimated RIR using S2IR-GAN (Ours) | Clean Speech | Reconstructed reverberant speech using estimated RIR | |
|---|---|---|---|---|---|---|
| Example 1 | ||||||
| Example 2 | ||||||
| Example 3 | ||||||
| Example 4 | ||||||
| Example 5 | ||||||
| Example 6 | ||||||
| Example 7 | ||||||
| Example 8 | ||||||
| Example 9 | ||||||
| Example 10 |
© October 2022
