From Senones to Chenones: Tied Context-Dependent Graphemes for Hybrid Speech Recognition

By Duc Le, Xiaohui Zhang, Weiyi Zheng, Christian Fügen, Geoffry Zweig, M. Seltzer. 2019

65 citations recorded by the source corpus.

There is an implicit assumption that traditional hybrid approaches for automatic speech recognition (ASR) cannot directly model graphemes and need to rely on phonetic lexicons to get competitive performance, especially on English which has poor grapheme-phoneme correspondence. In this work, we show for the first time that, on English, hybrid ASR systems can in fact model graphemes effectively by leveraging tied context-dependent graphemes, i.e., chenones. Our chenone-based systems significantly outperform equivalent senone baselines by 4.5% to 11.1% relative on three different English datasets. Our results on Librispeech are state-of-the-art compared to other hybrid approaches and competitive with previously published end-to-end numbers. Further analysis shows that chenones can better utilize powerful acoustic models and large training data, and require context- and position-dependent modeling to work well. Chenone-based systems also outperform senone baselines on proper noun and rare word recognition, an area where the latter is traditionally thought to have an advantage. Our work provides an alternative for end-to-end ASR and establishes that hybrid systems can be improved by dropping the reliance on phonetic knowledge.

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

In Speech & Audio

In Signal Processing

Citations in the corpus

HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units (2021, methodology): “We are comparing three k-means models learned from clustering MFCC teachers with 50, 100, 500 clusters, one learned from clustering HuBERT-BASE-it1 6th transformer layer features, and supervised labels obtained from the forced-alignment of character-based HMM models (chenone) [64].”
Transformer-Based Acoustic Modeling for Hybrid Speech Recognition (2019, methodology): “Following [24], we use context-and position-dependent graphemes (i.e., chenones ) in all experiments.”
Hubert: How Much Can a Bad Teacher Benefit ASR Pre-Training? (2021, methodology): “Finally, “Chenone” teacher uses a character-based hybrid ASR system trained on the full LibriSpeech data to derive forced-aligned chenone transcripts [43], which represents a supervised topline.”
Contrastive Semi-Supervised Learning for ASR (2021, methodology): “, (xT , yT ), where yi are represented as chenone units [24].”
Scaling Up Online Speech Recognition Using ConvNets (2020, methodology): “Baseline 1 The first baseline [23] is a hybrid system based on context-dependent graphemes (chenones) and uses multi-layer Latency Controlled Bidirectional Long Short-Term Memory layers (LC-BLSTM)[25] in the acoustic model.”
Fast, Simpler and More Accurate Hybrid ASR Systems Using Wordpieces (2020, methodology): “We follow the setup in [6] and use stride 2 for the chenone-CE baseline.”