E2E Segmenter: Joint Segmenting and Decoding for Long-Form ASR
| Autor: | W. Ronny Huang, Shuo-Yiin Chang, David Rybach, Tara Sainath, Rohit Prabhavalkar, Cal Peyser, Zhiyun Lu, Cyril Allauzen |
|---|---|
| Rok vydání: | 2022 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Machine Learning Sound (cs.SD) Computer Science - Computation and Language Audio and Speech Processing (eess.AS) FOS: Electrical engineering electronic engineering information engineering Computation and Language (cs.CL) Computer Science - Sound Electrical Engineering and Systems Science - Audio and Speech Processing Machine Learning (cs.LG) |
| DOI: | 10.48550/arxiv.2204.10749 |
| Popis: | Improving the performance of end-to-end ASR models on long utterances ranging from minutes to hours in length is an ongoing challenge in speech recognition. A common solution is to segment the audio in advance using a separate voice activity detector (VAD) that decides segment boundary locations based purely on acoustic speech/non-speech information. VAD segmenters, however, may be sub-optimal for real-world speech where, e.g., a complete sentence that should be taken as a whole may contain hesitations in the middle ("set an alarm for... 5 o'clock"). We propose to replace the VAD with an end-to-end ASR model capable of predicting segment boundaries in a streaming fashion, allowing the segmentation decision to be conditioned not only on better acoustic features but also on semantic features from the decoded text with negligible extra computation. In experiments on real world long-form audio (YouTube) with lengths of up to 30 minutes, we demonstrate 8.5% relative WER improvement and 250 ms reduction in median end-of-segment latency compared to the VAD segmenter baseline on a state-of-the-art Conformer RNN-T model. Comment: Interspeech 2022 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|