Tootfinder

Zero-shot Context Biasing with Trie-based Decoding using Synthetic Multi-Pronunciation
Changsong Liu, Yizhou Peng, Eng Siong Chng
https://arxiv.org/abs/2508.17796 https://

Zero-shot Context Biasing with Trie-based Decoding using Synthetic Multi-Pronunciation
Contextual automatic speech recognition (ASR) systems allow for recognizing out-of-vocabulary (OOV) words, such as named entities or rare words. However, it remains challenging due to limited training data and ambiguous or inconsistent pronunciations. In this paper, we propose a synthesis-driven multi-pronunciation contextual biasing method that performs zero-shot contextual ASR on a pretrained Whisper model. Specifically, we leverage text-to-speech (TTS) systems to synthesize diverse speech sa…

Automatic Pronunciation Error Detection and Correction of the Holy Quran's Learners Using Deep Learning
Abdullah Abdelfattah, Mahmoud I. Khalil, Hazem Abbas
https://arxiv.org/abs/2509.00094

Automatic Pronunciation Error Detection and Correction of the Holy Quran's Learners Using Deep Learning
Assessing spoken language is challenging, and quantifying pronunciation metrics for machine learning models is even harder. However, for the Holy Quran, this task is simplified by the rigorous recitation rules (tajweed) established by Muslim scholars, enabling highly effective assessment. Despite this advantage, the scarcity of high-quality annotated data remains a significant barrier. In this work, we bridge these gaps by introducing: (1) A 98% automated pipeline to produce high-quality Qura…

@… prepared for complaints about the proper pronunciation of "shout"

The dude writing Colorado State's official press guide pronunciation table's got jokes. 😁

#coloradostate #humor #football

Pronunciation Editing for Finnish Speech using Phonetic Posteriorgrams
Zirui Li, Lauri Juvela, Mikko Kurimo
https://arxiv.org/abs/2507.02115 https://

Pronunciation Editing for Finnish Speech using Phonetic Posteriorgrams
Synthesizing second-language (L2) speech is potentially highly valued for L2 language learning experience and feedback. However, due to the lack of L2 speech synthesis datasets, it is difficult to synthesize L2 speech for low-resourced languages. In this paper, we provide a practical solution for editing native speech to approximate L2 speech and present PPG2Speech, a diffusion-based multispeaker Phonetic-Posteriorgrams-to-Speech model that is capable of editing a single phoneme without text al…

V(is)owel: An Interactive Vowel Chart to Understand What Makes Visual Pronunciation Effective in Second Language Learning
Charlotte Kiesel, Dipayan Mukherjee, Mark Hasegawa-Johnson, Karrie Karahalios
https://arxiv.org/abs/2507.06202

V(is)owel: An Interactive Vowel Chart to Understand What Makes Visual Pronunciation Effective in Second Language Learning
Visual feedback speeds up learners' improvement of pronunciation in a second language. The visual combined with audio allows speakers to see sounds and differences in pronunciation that they are unable to hear. Prior studies have tested different visual methods for improving pronunciation, however, we do not have conclusive understanding of what aspects of the visualizations contributed to improvements. Based on previous work, we created V(is)owel, an interactive vowel chart. Vowel charts provi…

Parallel Needleman-Wunsch on CUDA to measure word similarity based on phonetic transcriptions
Dominic Plein
https://arxiv.org/abs/2509.01654 https://arxiv.…

Parallel Needleman-Wunsch on CUDA to measure word similarity based on phonetic transcriptions
We present a method to calculate the similarity between words based on their phonetic transcription (their pronunciation) using the Needleman-Wunsch algorithm. We implement this algorithm in Rust and parallelize it on both CPU and GPU to handle large datasets efficiently. The GPU implementation leverages CUDA and the cudarc Rust library to achieve significant performance improvements. We validate our approach by constructing a fully-connected graph where nodes represent words and edges have wei…

Towards stable AI systems for Evaluating Arabic Pronunciations
Hadi Zaatiti, Hatem Hajri, Osama Abdullah, Nader Masmoudi
https://arxiv.org/abs/2508.19587 https://

Towards stable AI systems for Evaluating Arabic Pronunciations
Modern Arabic ASR systems such as wav2vec 2.0 excel at word- and sentence-level transcription, yet struggle to classify isolated letters. In this study, we show that this phoneme-level task, crucial for language learning, speech therapy, and phonetic research, is challenging because isolated letters lack co-articulatory cues, provide no lexical context, and last only a few hundred milliseconds. Recogniser systems must therefore rely solely on variable acoustic cues, a difficulty heightened by A…

Segmentation-free Goodness of Pronunciation
Xinwei Cao, Zijian Fan, Torbj{\o}rn Svendsen, Giampiero Salvi
https://arxiv.org/abs/2507.16838 https://arxiv.or…

Segmentation-free Goodness of Pronunciation
Mispronunciation detection and diagnosis (MDD) is a significant part in modern computer aided language learning (CALL) systems. Within MDD, phoneme-level pronunciation assessment is key to helping L2 learners improve their pronunciation. However, most systems are based on a form of goodness of pronunciation (GOP) which requires pre-segmentation of speech into phonetic units. This limits the accuracy of these methods and the possibility to use modern CTC-based acoustic models for their evaluatio…

UtterTune: LoRA-Based Target-Language Pronunciation Edit and Control in Multilingual Text-to-Speech
Shuhei Kato
https://arxiv.org/abs/2508.09767 https://ar…

UtterTune: LoRA-Based Target-Language Pronunciation Edit and Control in Multilingual Text-to-Speech
We propose UtterTune, a lightweight adaptation method that fine-tunes a multilingual text-to-speech (TTS) system based on a large language model (LLM) architecture, designed to enhance the controllability of pronunciation in a target language while preserving performance in others. While LLM architectures have enabled TTS models to achieve remarkable naturalness, accurately modeling grapheme-to-phoneme (G2P) mapping and prosody remains challenging, especially when the model omits an explicit G2…