arXiv Computation and Language

Evaluation of Phonetic Encoding Algorithms on Transcription Datasets

The paper introduces a new evaluation framework for phonetic encoding algorithms, using a generalized Rand Index called the Hüllermeier‑Rifqi Index. It measures discordance by comparing pairwise similarity scores of ground‑truth IPA transcriptions with those of encoded strings, adjusted against a random generator. The method is applied to multilingual datasets, assessing recall via collision rate and demonstrating its use in evaluating orthographic transparency.

arXiv AI
1d ago

Flexible and Interpretable Accent Distance Measurements

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.

By Charles McGhee, Mark J. F. Gales, Kate M. Knill
arXiv Computation and Language
2d ago

Unadapted Multilingual ASR on a Garrusi Kurdish Evaluation Set: A Common-Reference Staged Normalization Analysis

The paper evaluates a multilingual ASR model (MMS‑1B‑all) on a Garrusi Kurdish dataset using a common‑reference staged normalization approach. By normalizing both reference and hypothesis, the authors show that raw Arabic‑script hypotheses yield a 111.70 % WER, which drops to 97.85 % after folding into a reduced orthography, highlighting the impact of orthographic differences on error measurement. A Southern Kurdish fine‑tuned system performs worse, and residual errors are partly due to scoring‑pipeline limitations rather than recognition failures.

By Hiwa Asadpour
arXiv Computation and Language
6d ago

Self-Supervised Lexical Representation Learning for Fast, Large-Scale Phylogenetic Inference

The paper presents a fully self‑supervised contrastive learning framework that learns lexical representations from raw IPA‑transcribed wordlists without any cognacy annotations or expert input. Using a dual contrastive objective—word‑level and language‑level losses—the model produces word representations that enable fast computation of pairwise language distances and the inference of a global phylogenetic tree for 3,399 language varieties. The resulting tree achieves a generalized quartet distance competitive with baselines while requiring only minutes of computation on a standard notebook GPU, and the representations also capture diachronic concept stability.

By Tim Wientzek
arXiv Machine Learning
Jul 14

An Empirical Recipe for Universal Phone Recognition

arXiv:2603. 29042v2 Announce Type: replace-cross Abstract: Phone recognition (PR) is a key enabler of multilingual and low-resource speech processing tasks, yet robust performance remains elusive.

By Shikhar Bharadwaj, Chin-Jou Li, Kwanghee Choi, Eunjung Yeo, William Chen, Shinji Watanabe, David R. Mortensen
arXiv Machine Learning
6d ago

Low-Latency Spell Correction for Japanese Music Search Queries

The paper introduces a compact BART-based sequence‑to‑sequence model for low‑latency spell correction of Japanese music search queries, addressing challenges posed by four writing scripts. It employs a script‑aware synthetic misspelling pipeline that blends keyboard‑layout models, phonetic confusion priors, consonant alternations, and kana case errors, and normalizes mixed‑script titles to a single canonical script to reduce hallucinations. Experiments show the model achieves 41.09% exact‑match accuracy and 11.62% CER, outperforming edit‑distance baselines while keeping inference latency under 4 ms on a single GPU.

By Anshul Garg, Pavni Tandon, Karan Bhukar, Tanmay Khandelwal, Ujjal Kumar Dutta
arXiv Computation and Language
Aug 28

Scaling phoneme-based TTS augmentation for ASR: A unified pipeline and controlled study

The paper introduces a unified phoneme‑based TTS‑to‑ASR augmentation pipeline that uses a multilingual TTS model with language‑ID conditioning and incorporates grapheme‑to‑phoneme conversion, reference‑speech filtering, and candidate‑text selection. It proposes phoneme‑frequency‑guided selection (PFGS) to rank sentences based on phoneme frequencies from real ASR labels, and demonstrates that random augmentation and PFGS both improve ASR performance across Arabic, French, Italian, and Portuguese test sets, with PFGS yielding up to a 19.3% relative WER reduction. The study also shows that filtering reference speech can further lower WER by up to 0.59 points on certain datasets.

By Zhen Wang, TianRui Wu, RongQi Han, Hao Wu, Wei Liang