An official website of the United States government
Current leading mispronunciation detection and diagnosis (MDD) systems achieve promising performance via end-to-end phoneme recognition. One challenge of such end-to-end solutions is the scarcity of human-annotated phonemes on natural L2 speech. In this work, we leverage unlabeled L2 speech via a pseudo-labeling (PL) procedure and extend the fine-tuning approach based on pre-trained self-supervised learning (SSL) models. Specifically, we use Wav2vec 2.0 as our SSL model, and fine-tune it using original labeled L2 speech samples plus the created pseudo-labeled L2 speech samples. Our pseudo labels are dynamic and are produced by an ensemble of the online model on-the-fly, which ensures that our model is robust to pseudo label noise. We show that fine-tuning with pseudo labels achieves a 5.35% phoneme error rate reduction and 2.48% MDD F1 score improvement over a labeled-samples-only finetuning baseline. The proposed PL method is also shown to outperform conventional offline PL methods. Compared to the state-of-the-art MDD systems, our MDD solution produces a more accurate and consistent phonetic error diagnosis. In addition, we conduct an open test on a separate UTD-4Accents dataset, where our system recognition outputs show a strong correlation with human perception, based on accentedness and intelligibility.
more »
« less
This content will become publicly available on November 15, 2025
Self-supervised speech representations display some human-like cross-linguistic perceptual abilities
State of the art models in automatic speech recognition have shown remarkable improvements due to modern self-supervised (SSL) transformer-based architectures such as wav2vec 2.0 (Baevski et al., 2020). However, how these models encode phonetic information is still not well understood. We explore whether SSL speech models display a linguistic property that characterizes human speech perception: language specificity. We show that while wav2vec 2.0 displays an overall language specificity effect when tested on Hindi vs. English, it does not resemble human speech perception when tested on finer-grained differences in Hindi speech contrasts.
more »
« less
- Award ID(s):
- 2120834
- PAR ID:
- 10568027
- Publisher / Repository:
- Proceedings of the 28th Conference on Computational Natural Language Learning
- Date Published:
- Page Range / eLocation ID:
- 458-463
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Comparing human and machine's use of coarticulatory vowel nasalization for linguistic classificationAnticipatory coarticulation is a highly informative cue to upcoming linguistic information: listeners can identify that the word is ben and not bed by hearing the vowel alone. The present study compares the relative performances of human listeners and a self-supervised pre-trained speech model (wav2vec 2.0) in the use of nasal coarticulation to classify vowels. Stimuli consisted of nasalized (from CVN words) and non-nasalized (from CVCs) American English vowels produced by 60 humans and generated in 36 TTS voices. wav2vec 2.0 performance is similar to human listener performance, in aggregate. Broken down by vowel type: both wav2vec 2.0 and listeners perform higher for non-nasalized vowels produced naturally by humans. However, wav2vec 2.0 shows higher correct classification performance for nasalized vowels, than for non-nasalized vowels, for TTS voices. Speaker-level patterns reveal that listeners' use of coarticulation is highly variable across talkers. wav2vec 2.0 also shows cross-talker variability in performance. Analyses also reveal differences in the use of multiple acoustic cues in nasalized vowel classifications across listeners and the wav2vec 2.0. Findings have implications for understanding how coarticulatory variation is used in speech perception. Results also can provide insight into how neural systems learn to attend to the unique acoustic features of coarticulation.more » « less
-
Recently, speech foundation models have gained popularity due to their superiority in finetuning downstream ASR tasks. However, models finetuned on certain domains, such as LibriSpeech (adult read speech), behave poorly on other domains (child or noisy speech). One solution could be collecting as much labeled and diverse data as possible for joint finetuning on various domains. However, collecting target domain speech-text paired data and retraining the model is often costly and computationally expensive. In this paper, we introduce a simple yet effective method, speech only adaptation (SOA), based on speech foundation models (Wav2vec 2.0), which requires only speech input data from the target domain. Specifically, the Wav2vec 2.0 feature encoder is continually pretrained with the Wav2vec 2.0 loss on both the source and target domain data for domain adaptation, while the contextual encoder is frozen. Compared to a source domain finetuned model with the feature encoder being frozen during training, we find that replacing the frozen feature encoder with the adapted one provides significant WER improvements to the target domain while preserving the performance of the source domain. The effectiveness of SOA is examined on various low resource or domain mismatched ASR settings, including adult-child and clean-noisy speech.more » « less
-
This paper presents a state-of-the-art model for transcribing speech in any language into the International Phonetic Alphabet (IPA). Transcription of spoken languages into IPA is an essential yet time-consuming process in language documentation, and even partially automating this process has the potential to drastically speed up the documentation of endangered languages. Like the previous best speech-to-IPA model (Wav2Vec2Phoneme), our model is based on wav2vec 2.0 and is fine-tuned to predict IPA from audio input. We use training data from seven languages from CommonVoice 11.0, transcribed into IPA semi-automatically. Although this training dataset is much smaller than Wav2Vec2Phoneme's, its higher quality lets our model achieve comparable or better results. Furthermore, we show that the quality of our universal speech-to-IPA models is close to that of human annotators.more » « less
-
Purpose The “bubble noise” technique has recently been introduced as a method to identify the regions in time–frequency maps (i.e., spectrograms) of speech that are especially important for listeners in speech recognition. This technique identifies regions of “importance” that are specific to the speech stimulus and the listener, thus permitting these regions to be compared across different listener groups. For example, in cross-linguistic and second-language (L2) speech perception, this method identifies differences in regions of importance in accomplishing decisions of phoneme category membership. This research note describes the application of bubble noise to the study of language learning for 3 different language pairs: Hindi English bilinguals' perception of the /v/–/w/ contrast in American English, native English speakers' perception of the tense/lax contrast for Korean fricatives and affricates, and native English speakers' perception of Mandarin lexical tone. Conclusion We demonstrate that this technique provides insight on what information in the speech signal is important for native/first-language listeners compared to nonnative/L2 listeners. Furthermore, the method can be used to examine whether L2 speech perception training is effective in bringing the listener's attention to the important cues.more » « less
