Self-supervised Speech Representations Still Struggle with African American Vernacular English

• URL: http://arxiv.org/abs/2408.14262v1
• Date: Mon, 26 Aug 2024 13:29:25 GMT
• Title: Self-supervised Speech Representations Still Struggle with African American Vernacular English
• Authors: Kalvin Chang, Yi-Hui Chou, Jiatong Shi, Hsuan-Ming Chen, Nicole Holliday, Odette Scharenborg, David R. Mortensen,
• Abstract summary: Underperformance of ASR systems for speakers of marginalized language varieties is a well-documented phenomenon. We investigate whether or not the recent wave of Self-Supervised Learning speech models can close the gap in ASR performance between AAVE and Mainstream American English.
• Score: 28.223877889211803
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Underperformance of ASR systems for speakers of African American Vernacular English (AAVE) and other marginalized language varieties is a well-documented phenomenon, and one that reinforces the stigmatization of these varieties. We investigate whether or not the recent wave of Self-Supervised Learning (SSL) speech models can close the gap in ASR performance between AAVE and Mainstream American English (MAE). We evaluate four SSL models (wav2vec 2.0, HuBERT, WavLM, and XLS-R) on zero-shot Automatic Speech Recognition (ASR) for these two varieties and find that these models perpetuate the bias in performance against AAVE. Additionally, the models have higher word error rates on utterances with more phonological and morphosyntactic features of AAVE. Despite the success of SSL speech models in improving ASR for low resource varieties, SSL pre-training alone may not bridge the gap between AAVE and MAE. Our code is publicly available at https://github.com/cmu-llab/s3m-aave.

Related papers

• One Language, Many Gaps: Evaluating Dialect Fairness and Robustness of Large Language Models in Reasoning Tasks [55.35278531907263]
  We present the first study on Large Language Models' fairness and robustness to a dialect in canonical reasoning tasks. We hire AAVE speakers to rewrite seven popular benchmarks, such as HumanEval and GSM8K. We find that, compared to Standardized English, almost all of these widely used models show significant brittleness and unfairness to queries in AAVE.
  arXiv  Detail & Related papers  (2024-10-14T18:44:23Z)
• Self-supervised ASR Models and Features For Dysarthric and Elderly Speech Recognition [71.87998918300806]
  This paper explores approaches to integrate domain fine-tuned SSL pre-trained models and their features into TDNN and Conformer ASR systems. TDNN systems constructed by integrating domain-adapted HuBERT, wav2vec2-conformer or multi-lingual XLSR models consistently outperform standalone fine-tuned SSL pre-trained models. Consistent improvements in Alzheimer's Disease detection accuracy are also obtained using the DementiaBank Pitt elderly speech recognition outputs.
  arXiv  Detail & Related papers  (2024-07-03T08:33:39Z)
• Improving Speech Recognition for African American English With Audio Classification [17.785482810741367]
  We propose a new way to improve the robustness of a US English short-form speech recognizer using a small amount of out-of-domain data. Fine-tuning on this data results in a 38.5% relative word error rate disparity reduction between AAE and MAE without reducing MAE quality.
  arXiv  Detail & Related papers  (2023-09-16T19:57:45Z)
• ML-SUPERB: Multilingual Speech Universal PERformance Benchmark [73.65853301350042]
  Speech processing Universal PERformance Benchmark (SUPERB) is a leaderboard to benchmark the performance of Self-Supervised Learning (SSL) models on various speech processing tasks. This paper presents multilingual SUPERB, covering 143 languages (ranging from high-resource to endangered), and considering both automatic speech recognition and language identification. Similar to the SUPERB benchmark, we find speech SSL models can significantly improve performance compared to FBANK features.
  arXiv  Detail & Related papers  (2023-05-18T00:01:27Z)
• Self-supervised Neural Factor Analysis for Disentangling Utterance-level Speech Representations [30.293081541301746]
  Self-supervised learning (SSL) speech models such as wav2vec and HuBERT have demonstrated state-of-the-art performance on automatic speech recognition. We argue that the problem is caused by the lack of disentangled representations and an utterance-level learning objective. Our models outperform the current best model, WavLM, on all utterance-level non-semantic tasks on the SUPERB benchmark with only 20% of labeled data.
  arXiv  Detail & Related papers  (2023-05-14T08:26:24Z)
• The Ability of Self-Supervised Speech Models for Audio Representations [53.19715501273934]
  Self-supervised learning (SSL) speech models have achieved unprecedented success in speech representation learning. We conduct extensive experiments on abundant speech and non-speech audio datasets to evaluate the representation ability of state-of-the-art SSL speech models. Results show that SSL speech models could extract meaningful features of a wide range of non-speech audio, while they may also fail on certain types of datasets.
  arXiv  Detail & Related papers  (2022-09-26T15:21:06Z)
• VALUE: Understanding Dialect Disparity in NLU [50.35526025326337]
  We construct rules for 11 features of African American Vernacular English (AAVE) We recruit fluent AAVE speakers to validate each feature transformation via linguistic acceptability judgments. Experiments show that these new dialectal features can lead to a drop in model performance.
  arXiv  Detail & Related papers  (2022-04-06T18:30:56Z)
• Cross-lingual Self-Supervised Speech Representations for Improved Dysarthric Speech Recognition [15.136348385992047]
  This study explores the usefulness of using Wav2Vec self-supervised speech representations as features for training an ASR system for dysarthric speech. We train an acoustic model with features extracted from Wav2Vec, Hubert, and the cross-lingual XLSR model. Results suggest that speech representations pretrained on large unlabelled data can improve word error rate (WER) performance.
  arXiv  Detail & Related papers  (2022-04-04T17:36:01Z)
• Sequence-level self-learning with multiple hypotheses [53.04725240411895]
  We develop new self-learning techniques with an attention-based sequence-to-sequence (seq2seq) model for automatic speech recognition (ASR) In contrast to conventional unsupervised learning approaches, we adopt the emphmulti-task learning (MTL) framework. Our experiment results show that our method can reduce the WER on the British speech data from 14.55% to 10.36% compared to the baseline model trained with the US English data only.
  arXiv  Detail & Related papers  (2021-12-10T20:47:58Z)
• Continual-wav2vec2: an Application of Continual Learning for Self-Supervised Automatic Speech Recognition [0.23872611575805824]
  We present a method for continual learning of speech representations for multiple languages using self-supervised learning (SSL) Wav2vec models perform SSL on raw audio in a pretraining phase and then finetune on a small fraction of annotated data. We use ideas from continual learning to transfer knowledge from a previous task to speed up pretraining a new language task.
  arXiv  Detail & Related papers  (2021-07-26T10:39:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.