Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Neural Representations for Modeling Variation in Speech

About

Variation in speech is often quantified by comparing phonetic transcriptions of the same utterance. However, manually transcribing speech is time-consuming and error prone. As an alternative, therefore, we investigate the extraction of acoustic embeddings from several self-supervised neural models. We use these representations to compute word-based pronunciation differences between non-native and native speakers of English, and between Norwegian dialect speakers. For comparison with several earlier studies, we evaluate how well these differences match human perception by comparing them with available human judgements of similarity. We show that speech representations extracted from a specific type of neural model (i.e. Transformers) lead to a better match with human perception than two earlier approaches on the basis of phonetic transcriptions and MFCC-based acoustic features. We furthermore find that features from the neural models can generally best be extracted from one of the middle hidden layers than from the final layer. We also demonstrate that neural speech representations not only capture segmental differences, but also intonational and durational differences that cannot adequately be represented by a set of discrete symbols used in phonetic transcriptions.

Martijn Bartelds, Wietse de Vries, Faraz Sanal, Caitlin Richter, Mark Liberman, Martijn Wieling• 2020

Related benchmarks

TaskDatasetResultRank
Pathological speech intelligibility assessmentCOPAS Sentence
PCC0.7
36
Pathological speech intelligibility assessmentCOPAS Word
PCC0.51
36
Pathological speech intelligibility assessmentEasyCall Word
PCC0.83
24
Pathological speech intelligibility assessmentEasyCall Sentence
PCC0.86
24
Pathological speech intelligibility assessmentUASpeech Word
PCC0.97
24
Pathological speech intelligibility assessmentTORGO Word
PCC0.55
24
Pathological speech intelligibility assessmentTORGO Sentence
PCC0.9
24
Pathological speech intelligibility assessmentNeuroVoz Sentence
PCC0.75
24
Showing 8 of 8 rows

Other info

Follow for update