arXiv subjects

Manuel Giollo

Publications and source records attributed to Manuel Giollo.

4 recordsLinked to original sources

arXiv2025

Hallucination Benchmark for Speech Foundation Models

Hallucinations in automatic speech recognition (ASR) systems refer to fluent and coherent transcriptions produced by neural ASR models that are completely unrelated to the underlying acoustic input (i.e., the speech signal). While similar to conventional decoding errors in potentially compromising the usability of transcriptions for downstream applications, hallucinations can be more detrimental due to their preservation of syntactically and semantically plausible structure. This apparent coherence can mislead subsequent processing stages and introduce serious risks, particularly in critical domains such as healthcare and law. Conventional evaluation metrics are primarily centered on error-based metrics and fail to distinguish between phonetic inaccuracies and hallucinations. Consequently, there is a critical need for new evaluation frameworks that can effectively identify and assess models with a heightened propensity for generating hallucinated content. To this end, we introduce SHALLOW, the first benchmark framework that systematically categorizes and quantifies hallucination phenomena in ASR along four complementary axes: lexical, phonetic, morphological, and semantic. We define targeted metrics within each category to produce interpretable profiles of model behavior. Through evaluation across various architectures and speech domains, we have found that SHALLOW metrics correlate strongly with word error rate (WER) when recognition quality is high (i.e., low WER). Still, this correlation weakens substantially as WER increases. SHALLOW, therefore, captures fine-grained error patterns that WER fails to distinguish under degraded and challenging conditions. Our framework supports specific diagnosis of model weaknesses and provides feedback for model improvement beyond what aggregate error rates can offer.

cs.CL↗

arXiv2020

Improved Robustness to Disfluencies in RNN-Transducer Based Speech Recognition

Automatic Speech Recognition (ASR) based on Recurrent Neural Network Transducers (RNN-T) is gaining interest in the speech community. We investigate data selection and preparation choices aiming for improved robustness of RNN-T ASR to speech disfluencies with a focus on partial words. For evaluation we use clean data, data with disfluencies and a separate dataset with speech affected by stuttering. We show that after including a small amount of data with disfluencies in the training set the recognition accuracy on the tests with disfluencies and stuttering improves. Increasing the amount of training data with disfluencies gives additional gains without degradation on the clean data. We also show that replacing partial words with a dedicated token helps to get even better accuracy on utterances with disfluencies and stutter. The evaluation of our best model shows 22.5% and 16.4% relative WER reduction on those two evaluation sets.

cs.CL↗

arXiv2020

Bootstrap an end-to-end ASR system by multilingual training, transfer learning, text-to-text mapping and synthetic audio

Bootstrapping speech recognition on limited data resources has been an area of active research for long. The recent transition to all-neural models and end-to-end (E2E) training brought along particular challenges as these models are known to be data hungry, but also came with opportunities around language-agnostic representations derived from multilingual data as well as shared word-piece output representations across languages that share script and roots. We investigate here the effectiveness of different strategies to bootstrap an RNN-Transducer (RNN-T) based automatic speech recognition (ASR) system in the low resource regime, while exploiting the abundant resources available in other languages as well as the synthetic audio from a text-to-speech (TTS) engine. Our experiments demonstrate that transfer learning from a multilingual model, using a post-ASR text-to-text mapping and synthetic audio deliver additive improvements, allowing us to bootstrap a model for a new language with a fraction of the data that would otherwise be needed. The best system achieved a 46% relative word error rate (WER) reduction compared to the monolingual baseline, among which 25% relative WER improvement is attributed to the post-ASR text-to-text mappings and the TTS synthetic data.

eess.AS↗

arXiv2016

An expanded evaluation of protein function prediction methods shows an improvement in accuracy

Background: The increasing volume and variety of genotypic and phenotypic data is a major defining characteristic of modern biomedical sciences. At the same time, the limitations in technology for generating data and the inherently stochastic nature of biomolecular events have led to the discrepancy between the volume of data and the amount of knowledge gleaned from it. A major bottleneck in our ability to understand the molecular underpinnings of life is the assignment of function to biological macromolecules, especially proteins. While molecular experiments provide the most reliable annotation of proteins, their relatively low throughput and restricted purview have led to an increasing role for computational function prediction. However, accurately assessing methods for protein function prediction and tracking progress in the field remain challenging. Methodology: We have conducted the second Critical Assessment of Functional Annotation (CAFA), a timed challenge to assess computational methods that automatically assign protein function. One hundred twenty-six methods from 56 research groups were evaluated for their ability to predict biological functions using the Gene Ontology and gene-disease associations using the Human Phenotype Ontology on a set of 3,681 proteins from 18 species. CAFA2 featured significantly expanded analysis compared with CAFA1, with regards to data set size, variety, and assessment metrics. To review progress in the field, the analysis also compared the best methods participating in CAFA1 to those of CAFA2. Conclusions: The top performing methods in CAFA2 outperformed the best methods from CAFA1, demonstrating that computational function prediction is improving. This increased accuracy can be attributed to the combined effect of the growing number of experimental annotations and improved methods for function prediction.

q-bio.QM↗