arXiv:2607. 04154v1 Announce Type: cross Abstract: This paper explains the principles and provides examples of a new method for distinguishing between FAKE human speech synthesized by generative AI and natural speech.
Neural TTS systems can sound natural across languages, but naturalness does not guarantee the preservation of sound contrasts that distinguish words from their grammatical forms. Standard metrics like MOS do not test for this.
arXiv:2607. 01965v1 Announce Type: cross Abstract: Neural TTS systems can sound natural across languages, but naturalness does not guarantee the preservation of sound contrasts that distinguish words from their grammatical forms.
arXiv:2608.30823v1 Announce Type: cross Abstract: The vocal music of each language carries a distinctive sonic identity, even without instrumental accompaniment. We ask whether these differences are...
The paper introduces a method for measuring accent differences that balances interpretability and practicality. It proposes using articulatory representations obtained via articulatory inversion as an interpretable basis for accent comparison, while employing optimal transport to compare accents across any type of recording. This approach aims to overcome the limitations of traditional phonetic analyses and embedding‑based methods, which are either time‑consuming or non‑interpretable.
Real-time MRI makes it possible to observe vocal-tract articulation during speech, but mapping these articulatory patterns to phonetic and phonological categories remains challenging. We investigate whether PhonoQ, an audio-based model trained to recognize structured phonological features, provides useful information for audio--articulatory modeling.
arXiv:2607.18317v5 Announce Type: replace-cross Abstract: We present TTSYoruba, a rule-based concatenative diphone speech synthesizer for Yoruba, deployed at online as part of the YorubaName.com open...
The study examines whether English homophones differ in phonetic realization beyond spoken word duration. Analyzing 14,000 homophone tokens from American television news, it finds that pairs such as "weight" and "wait" exhibit distinct phonetic patterns that can be predicted from their meanings in context. These differences persist even after controlling for duration, and time‑normalized spectrograms prove effective for detecting such fine‑grained phonetic variation without relying on phonetic transcriptions.
The vocal music of each language carries a distinctive sonic identity, even without instrumental accompaniment. We ask whether these differences are measurable and traceable to specific phonemes. To t...
The study examines how English homophones—words that sound identical but have different meanings—are pronounced differently in spoken language. Analyzing 14,000 homophone tokens from American television news, researchers found that pairs such as "weight" and "wait" exhibit distinct phonetic realizations that can be predicted from their contextual meanings, even after controlling for word duration. Time‑normalized spectrograms proved effective for detecting these subtle differences without relying on phonetic transcriptions.
arXiv:2602.18899v4 Announce Type: replace-cross Abstract: Self-supervised speech models (S3Ms) are known to encode rich phonetic information, yet how this information is structured remains underexplo...
arXiv:2610.35432v1 Announce Type: new Abstract: Neural audio codecs are increasingly used to encode speech for integration with large language models. This paper investigates the phonetic representat...
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.