You Sound a Little Tense: L2 Tailored Clear TTS Using Durational Vowel Properties

• URL: http://arxiv.org/abs/2506.23367v1
• Date: Sun, 29 Jun 2025 18:55:05 GMT
• Title: You Sound a Little Tense: L2 Tailored Clear TTS Using Durational Vowel Properties
• Abstract summary: We present the first text-to-speech (TTS) system tailored to second language (L2) speakers.<n>We use duration differences between American English tense (longer) and lax (shorter) vowels to create a "clarity mode" for Matcha-TTS.
• Score: 3.0995661604265385
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present the first text-to-speech (TTS) system tailored to second language (L2) speakers. We use duration differences between American English tense (longer) and lax (shorter) vowels to create a "clarity mode" for Matcha-TTS. Our perception studies showed that French-L1, English-L2 listeners had fewer (at least 9.15%) transcription errors when using our clarity mode, and found it more encouraging and respectful than overall slowed down speech. Remarkably, listeners were not aware of these effects: despite the decreased word error rate in clarity mode, listeners still believed that slowing all target words was the most intelligible, suggesting that actual intelligibility does not correlate with perceived intelligibility. Additionally, we found that Whisper-ASR did not use the same cues as L2 speakers to differentiate difficult vowels and is not sufficient to assess the intelligibility of TTS systems for these individuals.

Related papers

• Covertly improving intelligibility with data-driven adaptations of speech timing [3.61940804174624]
  We take advantage of recent advancements in machine-generated speech allowing more precise control of speech rate.<n>We show that the temporal influence of speech rate prior to a target vowel contrast in fact manifests in a scissor-like pattern.<n>We build a data-driven text-to-speech algorithm that replicates this temporal structure on novel speech sequences.
  arXiv  Detail & Related papers  (2026-03-31T17:30:47Z)
• Different Time, Different Language: Revisiting the Bias Against Non-Native Speakers in GPT Detectors [0.9440878004466183]
  We show that the perplexity of texts from non-native speakers of Czech is not lower than that of native speakers.<n>We examine detectors from three separate families and find no systematic bias against non-native speakers.
  arXiv  Detail & Related papers  (2026-02-05T15:31:24Z)
• SpeechIQ: Speech Intelligence Quotient Across Cognitive Levels in Voice Understanding Large Language Models [76.07833875692722]
  Speech-based Intelligence Quotient (SIQ) is a new form of human cognition-inspired evaluation pipeline for voice understanding large language models.<n>Our framework represents a first-of-its-kind intelligence examination that bridges cognitive principles with voice-oriented benchmarks.
  arXiv  Detail & Related papers  (2025-07-25T15:12:06Z)
• Investigating large language models for their competence in extracting grammatically sound sentences from transcribed noisy utterances [1.3597551064547497]
  Humans exhibit remarkable cognitive abilities to separate semantically significant content from speech-specific noise. We investigate whether large language models (LLMs) can effectively perform analogical speech comprehension tasks.
  arXiv  Detail & Related papers  (2024-10-07T14:55:20Z)
• LearnerVoice: A Dataset of Non-Native English Learners' Spontaneous Speech [36.447412884392115]
  We publicly release LearnerVoice, a dataset consisting of 50.04 hours of audio and transcriptions of L2 learners' spontaneous speech. Our linguistic analysis reveals that transcriptions in our dataset contain L2S features, significantly more than native speech datasets. Fine-tuning whisper-small.en with LearnerVoice achieves a WER of 10.26%, 44.2% lower than vanilla whisper-small.en.
  arXiv  Detail & Related papers  (2024-07-05T06:25:54Z)
• Towards Unsupervised Speech Recognition Without Pronunciation Models [57.222729245842054]
  In this article, we tackle the challenge of developing ASR systems without paired speech and text corpora.<n>We experimentally demonstrate that an unsupervised speech recognizer can emerge from joint speech-to-speech and text-to-text masked token-infilling.<n>This innovative model surpasses the performance of previous unsupervised ASR models under the lexicon-free setting.
  arXiv  Detail & Related papers  (2024-06-12T16:30:58Z)
• You don't understand me!: Comparing ASR results for L1 and L2 speakers of Swedish [0.5249805590164903]
  We focus on the gap in performance between recognition results for native and non-native, read and spontaneous, Swedish utterances transcribed by different ASR services. We compare the recognition results using Word Error Rate and analyze the linguistic factors that may generate the observed transcription errors.
  arXiv  Detail & Related papers  (2024-05-22T06:24:55Z)
• Language Proficiency and F0 Entrainment: A Study of L2 English Imitation in Italian, French, and Slovak Speakers [48.3822861675732]
  This study explores F0 entrainment in second language (L2) English speech imitation during an Alternating Reading Task (ART) participants with Italian, French, and Slovak native languages imitated English utterances. Results indicate a nuanced relationship between L2 English proficiency and entrainment.
  arXiv  Detail & Related papers  (2024-04-16T10:10:19Z)
• Prosody in Cascade and Direct Speech-to-Text Translation: a case study on Korean Wh-Phrases [79.07111754406841]
  This work proposes using contrastive evaluation to measure the ability of direct S2TT systems to disambiguate utterances where prosody plays a crucial role. Our results clearly demonstrate the value of direct translation systems over cascade translation models.
  arXiv  Detail & Related papers  (2024-02-01T14:46:35Z)
• A study on native American English speech recognition by Indian listeners with varying word familiarity level [62.14295630922855]
  We have three kinds of responses from each listener while they recognize an utterance. From these transcriptions, word error rate (WER) is calculated and used as a metric to evaluate the similarity between the recognized and the original sentences. Speaker nativity wise analysis shows that utterances from speakers of some nativity are more difficult to recognize by Indian listeners compared to few other nativities.
  arXiv  Detail & Related papers  (2021-12-08T07:43:38Z)
• Weakly-supervised word-level pronunciation error detection in non-native English speech [14.430965595136149]
  weakly-supervised model for word-level mispronunciation detection in non-native (L2) English speech. Phonetically transcribed L2 speech is not required and we only need to mark mispronounced words. Compared to state-of-the-art approaches, we improve the accuracy of detecting word-level pronunciation errors in AUC metric by 30% on the GUT Isle Corpus of L2 Polish speakers, and by 21.5% on the Isle Corpus of L2 German and Italian speakers.
  arXiv  Detail & Related papers  (2021-06-07T10:31:53Z)
• LRSpeech: Extremely Low-Resource Speech Synthesis and Recognition [148.43282526983637]
  We develop LRSpeech, a TTS and ASR system for languages with low data cost. We conduct experiments on an experimental language (English) and a truly low-resource language (Lithuanian) to verify the effectiveness of LRSpeech. We are currently deploying LRSpeech into a commercialized cloud speech service to support TTS on more rare languages.
  arXiv  Detail & Related papers  (2020-08-09T08:16:33Z)
• See what I'm saying? Comparing Intelligent Personal Assistant use for Native and Non-Native Language Speakers [12.021912017203842]
  We aim to understand how IPAs currently support or hinder users. Interviews revealed that L2 speakers prioritised utterance planning around perceived linguistic limitations. L2 speakers see IPAs as insensitive to linguistic needs resulting in failed interaction. We discuss the need to tailor the IPA experience for L2 users, emphasising visual feedback whilst reducing the burden of language production.
  arXiv  Detail & Related papers  (2020-06-11T11:03:49Z)

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.