Improving RNN-Transducers with Acoustic LookAhead

Autor:	Unni, Vinit S., Mittal, Ashish, Jyothi, Preethi, Sarawagi, Sunita
Rok vydání:	2023
Předmět:	Computer Science - Computation and Language Computer Science - Machine Learning Electrical Engineering and Systems Science - Audio and Speech Processing
Druh dokumentu:	Working Paper
Popis:	RNN-Transducers (RNN-Ts) have gained widespread acceptance as an end-to-end model for speech to text conversion because of their high accuracy and streaming capabilities. A typical RNN-T independently encodes the input audio and the text context, and combines the two encodings by a thin joint network. While this architecture provides SOTA streaming accuracy, it also makes the model vulnerable to strong LM biasing which manifests as multi-step hallucination of text without acoustic evidence. In this paper we propose LookAhead that makes text representations more acoustically grounded by looking ahead into the future within the audio input. This technique yields a significant 5%-20% relative reduction in word error rate on both in-domain and out-of-domain evaluation sets. Comment: 5 pages, 1 fig, 7 tables, Proceedings of Interspeech 2023
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2307.05006 Zobrazit plný text záznamu View this record from Arxiv