On the limit of English conversational speech recognition

By Zolt'an Tuske, George Saon, Brian Kingsbury. 2021

55 citations recorded by the source corpus.

In our previous work we demonstrated that a single headed attention encoder-decoder model is able to reach state-of-the-art results in conversational speech recognition. In this paper, we further improve the results for both Switchboard 300 and 2000. Through use of an improved optimizer, speaker vector embeddings, and alternative speech representations we reduce the recognition errors of our LSTM system on Switchboard-300 by 4% relative. Compensation of the decoder model with the probability ratio approach allows more efficient integration of an external language model, and we report 5.9% and 11.5% WER on the SWB and CHM parts of Hub5'00 with very simple LSTM models. Our study also considers the recently proposed conformer, and more advanced self-attention based language models. Overall, the conformer shows similar performance to the LSTM; nevertheless, their combination and decoding with an improved LM reaches a new record on Switchboard-300, 5.0% and 10.0% WER on SWB and CHM. Our findings are also confirmed on Switchboard-2000, and a new state of the art is reported, practically reaching the limit of the benchmark.

Subfields: Artificial Intelligence, Speech & Audio, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Jinyu Li
2. Yu Zhang
3. Tara N. Sainath
4. Shinji Watanabe
5. Yonghui Wu
6. Dong Yu
7. Chung-Cheng Chiu
8. Quoc V. Le

In Speech & Audio

1. Jinyu Li
2. Yu Zhang
3. Tara N. Sainath
4. Yonghui Wu
5. Chung-Cheng Chiu
6. Shinji Watanabe
7. Ruoming Pang
8. Bo Li

In Signal Processing

1. Jinyu Li
2. Yu Zhang
3. Tara N. Sainath
4. Shinji Watanabe
5. Dong Yu
6. Yonghui Wu
7. Chung-Cheng Chiu
8. Bo Li

Citations in the corpus

• BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognition (2021, methodology): “LibriSpeech and Switchboard/Fisher: The performance of YT-U pre-trained models lag behind SoTA performance on the LibriSpeech and Switchboard/Fisher tasks.”
• End-to-End Speech Recognition: A Survey (2023, methodology): “Finally, when trained on Switchboard 300 h, the current best result, obtained with an E2E system [180] is 5.4% compared to 6.6% word error rate for the best hybrid system result [325] on the HUB5’00 Switchboard test set, in Fig.”