1 citations · 1 across the 8 of their papers we have counts for
10 papers
CircuitTree: Composing Circuits into A Syllable Transcriber
Jiankun Wei, Ewan Dunbar, Gerald Penn
The goal of circuit discovery is to decompose a monolithic neural network into tiny modular subnetworks which are interpretable in the sense that each does an identifiable subtask.…
Sparse Weight and Edge Circuit Discovery in Transformer-based Acoustic Models
Jiankun Wei, Ewan Dunbar, Gerald Penn
Transformer-based foundation models are powerful but opaque, motivating Mechanistic Interpretation methods to uncover the black-box by identifying small computation subgraphs respo…
Do speech foundation models really learn words?
Robin Huo, Ewan Dunbar
Self-supervised speech foundation models are now used in a wide array of downstream applications, including traditional speech recognition and as the basis for tokens in speech-awa…
DiscoPhon: Benchmarking the Unsupervised Discovery of Phoneme Inventories With Discrete Speech Units
Maxime Poli, Manel Khentout, Angelo Ortiz Tandazo +3
We introduce DiscoPhon, a multilingual benchmark for evaluating unsupervised phoneme discovery from discrete speech units. DiscoPhon covers 6 dev and 6 test languages, chosen to sp…
Investigating Transcription Normalization in the Faetar ASR Benchmark
Leo Peckham, Michael Ong, Naomi Nagy +1
We examine the role of transcription inconsistencies in the Faetar Automatic Speech Recognition benchmark, a challenging low-resource ASR benchmark. With the help of a small, hand-…
Iterative refinement, not training objective, makes HuBERT behave differently from wav2vec 2.0
Robin Huo, Ewan Dunbar
Self-supervised models for speech representation learning now see widespread use for their versatility and performance on downstream tasks, but the effect of model architecture on…
The Faetar Benchmark: Speech Recognition in a Very Under-Resourced Language
Michael Ong, Sean Robertson, Leo Peckham +7
We introduce the Faetar Automatic Speech Recognition Benchmark, a benchmark corpus designed to push the limits of current approaches to low-resource speech recognition. Faetar, a F…
Quantifying the Role of Textual Predictability in Automatic Speech Recognition
Sean Robertson, Gerald Penn, Ewan Dunbar
A long-standing question in automatic speech recognition research is how to attribute errors to the ability of a model to model the acoustics, versus its ability to leverage higher…
Bigger is not Always Better: The Effect of Context Size on Speech Pre-Training
Sean Robertson, Ewan Dunbar
It has been generally assumed in the automatic speech recognition (ASR) literature that it is better for models to have access to wider context windows. Yet, many of the potential…
Zero Resource Code-switched Speech Benchmark Using Speech Utterance Pairs For Multiple Spoken Languages
Kuan-Po Huang, Chih-Kai Yang, Yu-Kuan Fu +2
We introduce a new zero resource code-switched speech benchmark designed to directly assess the code-switching capabilities of self-supervised speech encoders. We showcase a baseli…