research area Speech and Natural Language Processingconference ASRU
content type paperpublished January 2024

Acoustic Model Fusion for End-to-end Speech Recognition

AuthorsZhihong Lei, Mingbin Xu, Shiyi Han, Leo Liu, Zhen Huang, Tim Ng, Yuanyuan Zhang, Ernest Pusateri, Mirko Hannemann, Yaqiao Deng, Man-Hung Siu

View publication

Recent advances in deep learning and automatic speech recognition (ASR) have enabled the end-to-end (E2E) ASR system and boosted its accuracy to a new level. The E2E systems implicitly model all conventional ASR components, such as the acoustic model (AM) and the language model (LM), in a single network trained on audio-text pairs. Despite this simpler system architecture, fusing a separate LM, trained exclusively on text corpora, into the E2E system has proven to be beneficial. However, the application of LM fusion presents certain drawbacks, such as its inability to address the domain mismatch issue inherent to the internal AM. Drawing inspiration from the concept of LM fusion, we propose the integration of an external AM into the E2E system to address the domain mismatch better. By implementing this novel approach, we have achieved a significant reduction in the word error rate, with an impressive drop of up to 14.3% across varied test sets. We also discovered that this AM fusion approach is particularly beneficial in enhancing named entity recognition.

Related readings and updates.

Enhancing CTC-based Speech Recognition with Diverse Modeling Units

In recent years, the evolution of end-to-end (E2E) automatic speech recognition (ASR) models has been remarkable, largely due to advances in deep learning architectures like transformer. On top of E2E systems, researchers have achieved substantial accuracy improvement by rescoring E2E model’s N-best hypotheses with a phoneme-based model. This raises an interesting question about where the improvements come from other than the system combination…
See paper details

Finding Local Destinations with Siri’s Regionally Specific Language Models for Speech Recognition

The accuracy of automatic speech recognition (ASR) systems has improved phenomenally over recent years, due to the widespread adoption of deep learning techniques. Performance improvements have, however, mainly been made in the recognition of general speech; whereas accurately recognizing named entities, like small local businesses, has remained a performance bottleneck. This article describes how we met that challenge, improving Siri’s ability to recognize names of local POIs by incorporating knowledge of the user’s location into our speech recognition system. Customized language models that take the user's location into account are known as geolocation-based language models (Geo-LMs). These models enable Siri to better estimate the user’s intended sequence of words by using not only the information provided by the acoustic model and a general LM (like in standard ASR) but also information about the POIs in the user’s surroundings.

See highlight details