Time-normalized f0 contours of Mandarin words in conversational speech have been shown to be predictable in part from their contextualized embeddings (CEs). The present study investigates whether CEs also predict spoken word duration for 7470 tokens of Mandarin monosyllabic CV words extracted from a Mandarin corpus of spontaneous speech.
arXiv:2609.25890v1 Announce Type: new Abstract: Short-to-long training is a simple curriculum for speech models, but its gains can be difficult to interpret. In speech token language models, length-b...
The neutral, or floating, tone of Mandarin Chinese is a tone with an enigmatic set of properties. It has been described as a reduced tone, or as a tone that sometimes is lexically fixed but that can also be toneless.
arXiv:2609. 21362v1 Announce Type: new Abstract: Conventional tokenizers represent text as characters or statistically derived subwords, overlooking the internal phonological structure of syllables and often requiring large vocabularies.
arXiv:2510.22172v2 Announce Type: replace-cross Abstract: The Continuous Integrate-and-Fire (CIF) mechanism provides effective alignment for non-autoregressive (NAR) speech recognition. This mechanis...
arXiv:2607. 04064v1 Announce Type: cross Abstract: Unsupervised syllabic tokenization aims to learn discrete syllabic tokens that capture latent linguistic content-related structure from raw speech.
The paper introduces a token‑level extension of Omni‑Temporal Classification (OTC) for automatic speech recognition, allowing unsupported tokens to be bypassed while preserving supervision for the rest of the word. Across 19 languages and three corpora, this token‑level OTC consistently outperforms standard CTC, achieving the lowest mean word error rate on every dataset and a 9.45% average relative WER reduction. A predictive‑entropy‑indexed schedule replaces epoch‑based relaxation, reducing training‑length dependence while maintaining performance.
Phonetic forced alignment is a key technique in phonetic research, yet existing alignment systems lack specialized models for low-resource language varieties. We address this by training text-dependent and text-independent aligners for Chengdu Mandarin using a 17-hour corpus and a custom G2P dictionary.
arXiv:2606. 11371v1 Announce Type: cross Abstract: Spoken language, whether produced by humans or large language models (LLM), unfolds over time with varying semantic content.
Recent advances in zero-shot text-to-speech (TTS) have substantially improved speech quality and voice cloning fidelity. However, many zero-shot TTS systems still depend on audio prompt transcripts at inference time.
The paper introduces a continuous‑time approach to acoustic modeling in text‑to‑speech (TTS) using neural controlled differential equations (CDEs). It treats phone representations as temporally parameterized control paths and employs a neural acoustic vector field to generate hidden states that evolve continuously with phonetic content and duration. Experiments show that CDE‑based models can improve emotion‑intensity ranking while preserving expression quality, and that adjusting temporal resolution affects style tracking versus calibration.
arXiv:2607. 09020v1 Announce Type: cross Abstract: Phone segmentation and recognition are inherently related tasks, yet modern approaches typically model them separately.
arXiv:2609.22452v1 Announce Type: new Abstract: Long-context understanding remains a fundamental challenge for large language models, as excessively long inputs often lead models to forget salient in...