Knowing What to Stress: A Discourse-Conditioned Text-to-Speech Benchmark

• URL: http://arxiv.org/abs/2604.10580v1
• Date: Sun, 12 Apr 2026 10:57:00 GMT
• Title: Knowing What to Stress: A Discourse-Conditioned Text-to-Speech Benchmark
• Abstract summary: We present Context-Aware Stress TTS (CAST), a benchmark for evaluating context-conditioned word-level stress in TTS.<n>We evaluate state-of-the-art systems and find a consistent gap: text-only language models reliably recover the intended stress from context, yet TTS systems frequently fail to realize it in speech.
• Score: 33.2356561675589
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Spoken meaning often depends not only on what is said, but also on which word is emphasized. The same sentence can convey correction, contrast, or clarification depending on where emphasis falls. Although modern text-to-speech (TTS) systems generate expressive speech, it remains unclear whether they infer contextually appropriate stress from discourse alone. To address this gap, we present Context-Aware Stress TTS (CAST), a benchmark for evaluating context-conditioned word-level stress in TTS. Items are defined as contrastive context pairs: identical sentences paired with distinct contexts requiring different stressed words. We evaluate state-of-the-art systems and find a consistent gap: text-only language models reliably recover the intended stress from context, yet TTS systems frequently fail to realize it in speech. We release the benchmark, evaluation framework, construction pipeline and a synthetic corpus to support future work on context-aware speech synthesis.

Related papers

• Do Spoken Language Models Hear Speech as They Read Text? Bridging Structural Gaps Between Speech and Text [3.1208668217678355]
  Spoken Language Models generate textual responses directly from speech.<n>Existing SLMs exhibit weaker instruction-following behavior and limited generalization.<n>We propose a simple framework that decouples length mismatch from semantic alignment.
  arXiv  Detail & Related papers  (2026-08-24T07:41:28Z)
• How to Recognize New Words: A Comparison Between Context Biasing Methods and Speech LLMs [61.601626186678146]
  We evaluate two context biasing methods based on Whisper against three speech large language models (LLMs)<n>The context biasing methods cut biased WER by up to 88% relative while leaving other words largely unaffected.<n> Speech LLMs excel on read speech but generalize less well to non-read speech, and prove sensitive to distractor count and prompt word order.
  arXiv  Detail & Related papers  (2026-08-06T08:45:33Z)
• MOSS-Speech: Towards True Speech-to-Speech Models Without Text Guidance [66.74042564585942]
  MOSS-Speech is a true speech-to-speech large language model that directly understands and generates speech without relying on text guidance.<n>Our work establishes a new paradigm for expressive and efficient end-to-end speech interaction.
  arXiv  Detail & Related papers  (2025-10-01T04:32:37Z)
• LibriQuote: A Speech Dataset of Fictional Character Utterances for Expressive Zero-Shot Speech Synthesis [9.933931058173014]
  We introduce the LibriQuote dataset, an English corpus derived from read audiobooks.<n>The training dataset includes 12.7K hours of read, non-expressive speech and 5.3K hours of mostly expressive speech drawn from character quotations.<n>We also provide a challenging 7.5 hour test set intended for benchmarking TTS systems.
  arXiv  Detail & Related papers  (2025-09-04T10:05:06Z)
• WHISTRESS: Enriching Transcriptions with Sentence Stress Detection [20.802090523583196]
  Sentence stress is crucial for conveying speaker intent in spoken language.<n>We introduce WHISTRESS, an alignment-free approach for enhancing transcription systems with sentence stress detection.<n>We train WHISTRESS on TINYSTRESS-15K and evaluate it against several competitive baselines.
  arXiv  Detail & Related papers  (2025-05-25T11:45:08Z)
• Towards Emotionally Consistent Text-Based Speech Editing: Introducing EmoCorrector and The ECD-TSE Dataset [52.95197015472105]
  EmoCorrector is a novel post-correction scheme for text-based speech editing.<n>It retrieves the edited text's emotional features, retrieving speech samples with matching emotions, and synthesizing speech that aligns with the desired emotion.<n>EmoCorrector significantly enhances the expression of intended emotion while addressing emotion inconsistency limitations in current TSE methods.
  arXiv  Detail & Related papers  (2025-05-24T16:10:56Z)
• A Preliminary Analysis of Automatic Word and Syllable Prominence Detection in Non-Native Speech With Text-to-Speech Prosody Embeddings [9.764748000637082]
  Automatic detection of prominence at the word and syllable-levels is critical for building computer-assisted language learning systems.<n>It has been shown that prosody embeddings learned by the current state-of-the-art (SOTA) text-to-speech (TTS) systems could generate word- and syllable-level prominence in the synthesized speech as natural as in native speech.
  arXiv  Detail & Related papers  (2024-12-11T10:58:14Z)
• ContextSpeech: Expressive and Efficient Text-to-Speech for Paragraph Reading [65.88161811719353]
  This work develops a lightweight yet effective Text-to-Speech system, ContextSpeech. We first design a memory-cached recurrence mechanism to incorporate global text and speech context into sentence encoding. We construct hierarchically-structured textual semantics to broaden the scope for global context enhancement. Experiments show that ContextSpeech significantly improves the voice quality and prosody in paragraph reading with competitive model efficiency.
  arXiv  Detail & Related papers  (2023-07-03T06:55:03Z)
• Contextual Expressive Text-to-Speech [25.050361896378533]
  We introduce a new task setting, Contextual Text-to-speech (CTTS) The main idea of CTTS is that how a person speaks depends on the particular context she is in, where the context can typically be represented as text. We construct a synthetic dataset and develop an effective framework to generate high-quality expressive speech based on the given context.
  arXiv  Detail & Related papers  (2022-11-26T12:06:21Z)
• FCTalker: Fine and Coarse Grained Context Modeling for Expressive Conversational Speech Synthesis [75.74906149219817]
  Conversational Text-to-Speech (TTS) aims to synthesis an utterance with the right linguistic and affective prosody in a conversational context. We propose a novel expressive conversational TTS model, as termed FCTalker, that learn the fine and coarse grained context dependency at the same time during speech generation.
  arXiv  Detail & Related papers  (2022-10-27T12:20:20Z)

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.