Odette Scharenborg

Kalvin Chang, Yi-Hui Chou, Jiatong Shi et al. · cmu

Underperformance of ASR systems for speakers of African American Vernacular English (AAVE) and other marginalized language varieties is a well-documented phenomenon, and one that reinforces the stigmatization of these varieties. We investigate whether or not the recent wave of Self-Supervised Learning (SSL) speech models can close the gap in ASR performance between AAVE and Mainstream American English (MAE). We evaluate four SSL models (wav2vec 2.0, HuBERT, WavLM, and XLS-R) on zero-shot Automatic Speech Recognition (ASR) for these two varieties and find that these models perpetuate the bias in performance against AAVE. Additionally, the models have higher word error rates on utterances with more phonological and morphosyntactic features of AAVE. Despite the success of SSL speech models in improving ASR for low resource varieties, SSL pre-training alone may not bridge the gap between AAVE and MAE. Our code is publicly available at https://github.com/cmu-llab/s3m-aave.

Tanvina Patel, Odette Scharenborg

Speech technology has improved greatly for norm speakers, i.e., adult native speakers of a language without speech impediments or strong accents. However, non-norm or diverse speaker groups show a distinct performance gap with norm speakers, which we refer to as bias. In this work, we aim to reduce bias against different age groups and non-native speakers of Dutch. For an end-to-end (E2E) ASR system, we use state-of-the-art speed perturbation and spectral augmentation as data augmentation techniques and explore Vocal Tract Length Normalization (VTLN) to normalise for spectral differences due to differences in anatomy. The combination of data augmentation and VTLN reduced the average WER and bias across various diverse speaker groups by 6.9% and 3.9%, respectively. The VTLN model trained on Dutch was also effective in improving performance of Mandarin Chinese child speech, thus, showing generalisability across languages

Danny Merkx, Sebastiaan Scholten, Stefan L. Frank et al.

Background: Computational models of speech recognition often assume that the set of target words is already given. This implies that these models do not learn to recognise speech from scratch without prior knowledge and explicit supervision. Visually grounded speech models learn to recognise speech without prior knowledge by exploiting statistical dependencies between spoken and visual input. While it has previously been shown that visually grounded speech models learn to recognise the presence of words in the input, we explicitly investigate such a model as a model of human speech recognition. Methods: We investigate the time-course of word recognition as simulated by the model using a gating paradigm to test whether its recognition is affected by well-known word-competition effects in human speech processing. We furthermore investigate whether vector quantisation, a technique for discrete representation learning, aids the model in the discovery and recognition of words. Results/Conclusion: Our experiments show that the model is able to recognise nouns in isolation and even learns to properly differentiate between plural and singular nouns. We also find that recognition is influenced by word competition from the word-initial cohort and neighbourhood density, mirroring word competition effects in human speech comprehension. Lastly, we find no evidence that vector quantisation is helpful in discovering and recognising words. Our gating experiments even show that the vector quantised model requires more of the input sequence for correct recognition.

Ming Gao, Shilong Wu, Hang Chen et al. · gatech

Meetings are a valuable yet challenging scenario for speech applications due to complex acoustic conditions. This paper summarizes the outcomes of the MISP 2025 Challenge, hosted at Interspeech 2025, which focuses on multi-modal, multi-device meeting transcription by incorporating video modality alongside audio. The tasks include Audio-Visual Speaker Diarization (AVSD), Audio-Visual Speech Recognition (AVSR), and Audio-Visual Diarization and Recognition (AVDR). We present the challenge's objectives, tasks, dataset, baseline systems, and solutions proposed by participants. The best-performing systems achieved significant improvements over the baseline: the top AVSD model achieved a Diarization Error Rate (DER) of 8.09%, improving by 7.43%; the top AVSR system achieved a Character Error Rate (CER) of 9.48%, improving by 10.62%; and the best AVDR system achieved a concatenated minimum-permutation Character Error Rate (cpCER) of 11.56%, improving by 72.49%.

Luciana Ferrer, Odette Scharenborg, Tom Bäckström

Many development decisions affect the results obtained from ML experiments: training data, features, model architecture, hyperparameters, test data, etc. Among these aspects, arguably the most important design decisions are those that involve the evaluation procedure. This procedure is what determines whether the conclusions drawn from the experiments will or will not generalize to unseen data and whether they will be relevant to the application of interest. If the data is incorrectly selected, the wrong metric is chosen for evaluation or the significance of the comparisons between models is overestimated, conclusions may be misleading or result in suboptimal development decisions. To avoid such problems, the evaluation protocol should be very carefully designed before experimentation starts. In this work we discuss the main aspects involved in the design of the evaluation protocol: data selection, metric selection, and statistical significance. This document is not meant to be an exhaustive tutorial on each of these aspects. Instead, the goal is to explain the main guidelines that should be followed in each case. We include examples taken from the speech processing field, and provide a list of common mistakes related to each aspect.

Tanvina Patel, Wiebke Hutiri, Aaron Yi Ding et al.

There is increasingly more evidence that automatic speech recognition (ASR) systems are biased against different speakers and speaker groups, e.g., due to gender, age, or accent. Research on bias in ASR has so far primarily focused on detecting and quantifying bias, and developing mitigation approaches. Despite this progress, the open question is how to measure the performance and bias of a system. In this study, we compare different performance and bias measures, from literature and proposed, to evaluate state-of-the-art end-to-end ASR systems for Dutch. Our experiments use several bias mitigation strategies to address bias against different speaker groups. The findings reveal that averaged error rates, a standard in ASR research, alone is not sufficient and should be supplemented by other measures. The paper ends with recommendations for reporting ASR performance and bias to better represent a system's performance for diverse speaker groups, and overall system bias.

Yuanyuan Zhang, Zhengjun Yue, Tanvina Patel et al.

State-of-the-art ASRs show suboptimal performance for child speech. The scarcity of child speech limits the development of child speech recognition (CSR). Therefore, we studied child-to-child voice conversion (VC) from existing child speakers in the dataset and additional (new) child speakers via monolingual and cross-lingual (Dutch-to-German) VC, respectively. The results showed that cross-lingual child-to-child VC significantly improved child ASR performance. Experiments on the impact of the quantity of child-to-child cross-lingual VC-generated data on fine-tuning (FT) ASR models gave the best results with two-fold augmentation for our FT-Conformer model and FT-Whisper model which reduced WERs with ~3% absolute compared to the baseline, and with six-fold augmentation for the model trained from scratch, which improved by an absolute 3.6% WER. Moreover, using a small amount of "high-quality" VC-generated data achieved similar results to those of our best-FT models.

Bence Mark Halpern, Teja Rebernik, Thomas Tienkamp et al.

We present an articulatory synthesis framework for the synthesis and manipulation of oral cancer speech for clinical decision making and alleviation of patient stress. Objective and subjective evaluations demonstrate that the framework has acceptable naturalness and is worth further investigation. A subsequent subjective vowel and consonant identification experiment showed that the articulatory synthesis system can manipulate the articulatory trajectories so that the synthesised speech reproduces problems present in the ground truth oral cancer speech.

Piotr Żelasko, Siyuan Feng, Laureano Moro Velazquez et al.

The high cost of data acquisition makes Automatic Speech Recognition (ASR) model training problematic for most existing languages, including languages that do not even have a written script, or for which the phone inventories remain unknown. Past works explored multilingual training, transfer learning, as well as zero-shot learning in order to build ASR systems for these low-resource languages. While it has been shown that the pooling of resources from multiple languages is helpful, we have not yet seen a successful application of an ASR model to a language unseen during training. A crucial step in the adaptation of ASR from seen to unseen languages is the creation of the phone inventory of the unseen language. The ultimate goal of our work is to build the phone inventory of a language unseen during training in an unsupervised way without any knowledge about the language. In this paper, we 1) investigate the influence of different factors (i.e., model architecture, phonotactic model, type of speech representation) on phone recognition in an unknown language; 2) provide an analysis of which phones transfer well across languages and which do not in order to understand the limitations of and areas for further improvement for automatic phone inventory creation; and 3) present different methods to build a phone inventory of an unseen language in an unsupervised way. To that end, we conducted mono-, multi-, and crosslingual experiments on a set of 13 phonetically diverse languages and several in-depth analyses. We found a number of universal phone tokens (IPA symbols) that are well-recognized cross-linguistically. Through a detailed analysis of results, we conclude that unique sounds, similar sounds, and tone languages remain a major challenge for phonetic inventory discovery.

Luke Prananta, Bence Mark Halpern, Siyuan Feng et al.

In this paper, we investigate several existing and a new state-of-the-art generative adversarial network-based (GAN) voice conversion method for enhancing dysarthric speech for improved dysarthric speech recognition. We compare key components of existing methods as part of a rigorous ablation study to find the most effective solution to improve dysarthric speech recognition. We find that straightforward signal processing methods such as stationary noise removal and vocoder-based time stretching lead to dysarthric speech recognition results comparable to those obtained when using state-of-the-art GAN-based voice conversion methods as measured using a phoneme recognition task. Additionally, our proposed solution of a combination of MaskCycleGAN-VC and time stretched enhancement is able to improve the phoneme recognition results for certain dysarthric speakers compared to our time stretched baseline.

Wen-Chin Huang, Bence Mark Halpern, Lester Phillip Violeta et al.

We present a voice conversion framework that converts normal speech into dysarthric speech while preserving the speaker identity. Such a framework is essential for (1) clinical decision making processes and alleviation of patient stress, (2) data augmentation for dysarthric speech recognition. This is an especially challenging task since the converted samples should capture the severity of dysarthric speech while being highly natural and possessing the speaker identity of the normal speaker. To this end, we adopted a two-stage framework, which consists of a sequence-to-sequence model and a nonparallel frame-wise model. Objective and subjective evaluations were conducted on the UASpeech dataset, and results showed that the method was able to yield reasonable naturalness and capture severity aspects of the pathological speech. On the other hand, the similarity to the normal source speaker's voice was limited and requires further improvements.

Bence Mark Halpern, Julian Fritsch, Enno Hermann et al.

The development of pathological speech systems is currently hindered by the lack of a standardised objective evaluation framework. In this work, (1) we utilise existing detection and analysis techniques to propose a general framework for the consistent evaluation of synthetic pathological speech. This framework evaluates the voice quality and the intelligibility aspects of speech and is shown to be complementary using our experiments. (2) Using our proposed evaluation framework, we develop and test a dysarthric voice conversion system (VC) using CycleGAN-VC and a PSOLA-based speech rate modification technique. We show that the developed system is able to synthesise dysarthric speech with different levels of speech intelligibility.

Marc Illa, Bence Mark Halpern, Rob van Son et al.

In this paper, we propose a new approach to pathological speech synthesis. Instead of using healthy speech as a source, we customise an existing pathological speech sample to a new speaker's voice characteristics. This approach alleviates the evaluation problem one normally has when converting typical speech to pathological speech, as in our approach, the voice conversion (VC) model does not need to be optimised for speech degradation but only for the speaker change. This change in the optimisation ensures that any degradation found in naturalness is due to the conversion process and not due to the model exaggerating characteristics of a speech pathology. To show a proof of concept of this method, we convert dysarthric speech using the UASpeech database and an autoencoder-based VC technique. Subjective evaluation results show reasonable naturalness for high intelligibility dysarthric speakers, though lower intelligibility seems to introduce a marginal degradation in naturalness scores for mid and low intelligibility speakers compared to ground truth. Conversion of speaker characteristics for low and high intelligibility speakers is successful, but not for mid. Whether the differences in the results for the different intelligibility levels is due to the intelligibility levels or due to the speakers needs to be further investigated.

Siyuan Feng, Piotr Żelasko, Laureano Moro-Velázquez et al.

This paper tackles automatically discovering phone-like acoustic units (AUD) from unlabeled speech data. Past studies usually proposed single-step approaches. We propose a two-stage approach: the first stage learns a subword-discriminative feature representation and the second stage applies clustering to the learned representation and obtains phone-like clusters as the discovered acoustic units. In the first stage, a recently proposed method in the task of unsupervised subword modeling is improved by replacing a monolingual out-of-domain (OOD) ASR system with a multilingual one to create a subword-discriminative representation that is more language-independent. In the second stage, segment-level k-means is adopted, and two methods to represent the variable-length speech segments as fixed-dimension feature vectors are compared. Experiments on a very low-resource Mboshi language corpus show that our approach outperforms state-of-the-art AUD in both normalized mutual information (NMI) and F-score. The multilingual ASR improved upon the monolingual ASR in providing OOD phone labels and in estimating the phone boundaries. A comparison of our systems with and without knowing the ground-truth phone boundaries showed a 16% NMI performance gap, suggesting that the current approach can significantly benefit from improved phone boundary estimation.

Siyuan Feng, Olya Kudina, Bence Mark Halpern et al.

Automatic speech recognition (ASR) systems promise to deliver objective interpretation of human speech. Practice and recent evidence suggests that the state-of-the-art (SotA) ASRs struggle with the large variation in speech due to e.g., gender, age, speech impairment, race, and accents. Many factors can cause the bias of an ASR system. Our overarching goal is to uncover bias in ASR systems to work towards proactive bias mitigation in ASR. This paper is a first step towards this goal and systematically quantifies the bias of a Dutch SotA ASR system against gender, age, regional accents and non-native accents. Word error rates are compared, and an in-depth phoneme-level error analysis is conducted to understand where bias is occurring. We primarily focus on bias due to articulation differences in the dataset. Based on our findings, we suggest bias mitigation strategies for ASR development.

Siyuan Feng, Odette Scharenborg

This study addresses unsupervised subword modeling, i.e., learning acoustic feature representations that can distinguish between subword units of a language. We propose a two-stage learning framework that combines self-supervised learning and cross-lingual knowledge transfer. The framework consists of autoregressive predictive coding (APC) as the front-end and a cross-lingual deep neural network (DNN) as the back-end. Experiments on the ABX subword discriminability task conducted with the Libri-light and ZeroSpeech 2017 databases showed that our approach is competitive or superior to state-of-the-art studies. Comprehensive and systematic analyses at the phoneme- and articulatory feature (AF)-level showed that our approach was better at capturing diphthong than monophthong vowel information, while also differences in the amount of information captured for different types of consonants were observed. Moreover, a positive correlation was found between the effectiveness of the back-end in capturing a phoneme's information and the quality of the cross-lingual phone labels assigned to the phoneme. The AF-level analysis together with t-SNE visualization results showed that the proposed approach is better than MFCC and APC features in capturing manner and place of articulation information, vowel height, and backness information. Taken together, the analyses showed that the two stages in our approach are both effective in capturing phoneme and AF information. Nevertheless, monophthong vowel information is less well captured than consonant information, which suggests that future research should focus on improving capturing monophthong vowel information.

Si-Ioi Ng, Wei Liu, Zhiyuan Peng et al.

This technical report describes our submission to the 2021 SLT Children Speech Recognition Challenge (CSRC) Track 1. Our approach combines the use of a joint CTC-attention end-to-end (E2E) speech recognition framework, transfer learning, data augmentation and development of various language models. Procedures of data pre-processing, the background and the course of system development are described. The analysis of the experiment results, as well as the comparison between the E2E and DNN-HMM hybrid system are discussed in detail. Our system achieved a character error rate (CER) of 20.1% in our designated test set, and 23.6% in the official evaluation set, which is placed at 10-th overall.

Xinsheng Wang, Siyuan Feng, Jihua Zhu et al.

This paper proposes a new model, referred to as the show and speak (SAS) model that, for the first time, is able to directly synthesize spoken descriptions of images, bypassing the need for any text or phonemes. The basic structure of SAS is an encoder-decoder architecture that takes an image as input and predicts the spectrogram of speech that describes this image. The final speech audio is obtained from the predicted spectrogram via WaveNet. Extensive experiments on the public benchmark database Flickr8k demonstrate that the proposed SAS is able to synthesize natural spoken descriptions for images, indicating that synthesizing spoken descriptions for images while bypassing text and phonemes is feasible.

Siyuan Feng, Piotr Żelasko, Laureano Moro-Velázquez et al.

The idea of combining multiple languages' recordings to train a single automatic speech recognition (ASR) model brings the promise of the emergence of universal speech representation. Recently, a Transformer encoder-decoder model has been shown to leverage multilingual data well in IPA transcriptions of languages presented during training. However, the representations it learned were not successful in zero-shot transfer to unseen languages. Because that model lacks an explicit factorization of the acoustic model (AM) and language model (LM), it is unclear to what degree the performance suffered from differences in pronunciation or the mismatch in phonotactics. To gain more insight into the factors limiting zero-shot ASR transfer, we replace the encoder-decoder with a hybrid ASR system consisting of a separate AM and LM. Then, we perform an extensive evaluation of monolingual, multilingual, and crosslingual (zero-shot) acoustic and language models on a set of 13 phonetically diverse languages. We show that the gain from modeling crosslingual phonotactics is limited, and imposing a too strong model can hurt the zero-shot transfer. Furthermore, we find that a multilingual LM hurts a multilingual ASR system's performance, and retaining only the target language's phonotactic data in LM training is preferable.

Justin van der Hout, Zoltán D'Haese, Mark Hasegawa-Johnson et al.

Image2Speech is the relatively new task of generating a spoken description of an image. This paper presents an investigation into the evaluation of this task. For this, first an Image2Speech system was implemented which generates image captions consisting of phoneme sequences. This system outperformed the original Image2Speech system on the Flickr8k corpus. Subsequently, these phoneme captions were converted into sentences of words. The captions were rated by human evaluators for their goodness of describing the image. Finally, several objective metric scores of the results were correlated with these human ratings. Although BLEU4 does not perfectly correlate with human ratings, it obtained the highest correlation among the investigated metrics, and is the best currently existing metric for the Image2Speech task. Current metrics are limited by the fact that they assume their input to be words. A more appropriate metric for the Image2Speech task should assume its input to be parts of words, i.e. phonemes, instead.

Bence Mark Halpern, Rob van Son, Michiel van den Brekel et al.

Oral cancer speech is a disease which impacts more than half a million people worldwide every year. Analysis of oral cancer speech has so far focused on read speech. In this paper, we 1) present and 2) analyse a three-hour long spontaneous oral cancer speech dataset collected from YouTube. 3) We set baselines for an oral cancer speech detection task on this dataset. The analysis of these explainable machine learning baselines shows that sibilants and stop consonants are the most important indicators for spontaneous oral cancer speech detection.

Siyuan Feng, Odette Scharenborg

This study addresses unsupervised subword modeling, i.e., learning feature representations that can distinguish subword units of a language. The proposed approach adopts a two-stage bottleneck feature (BNF) learning framework, consisting of autoregressive predictive coding (APC) as a front-end and a DNN-BNF model as a back-end. APC pretrained features are set as input features to a DNN-BNF model. A language-mismatched ASR system is used to provide cross-lingual phone labels for DNN-BNF model training. Finally, BNFs are extracted as the subword-discriminative feature representation. A second aim of this work is to investigate the robustness of our approach's effectiveness to different amounts of training data. The results on Libri-light and the ZeroSpeech 2017 databases show that APC is effective in front-end feature pretraining. Our whole system outperforms the state of the art on both databases. Cross-lingual phone labels for English data by a Dutch ASR outperform those by a Mandarin ASR, possibly linked to the larger similarity of Dutch compared to Mandarin with English. Our system is less sensitive to training data amount when the training data is over 50 hours. APC pretraining leads to a reduction of needed training material from over 5,000 hours to around 200 hours with little performance degradation.

Sebastiaan Scholten, Danny Merkx, Odette Scharenborg

We investigated word recognition in a Visually Grounded Speech model. The model has been trained on pairs of images and spoken captions to create visually grounded embeddings which can be used for speech to image retrieval and vice versa. We investigate whether such a model can be used to recognise words by embedding isolated words and using them to retrieve images of their visual referents. We investigate the time-course of word recognition using a gating paradigm and perform a statistical analysis to see whether well known word competition effects in human speech processing influence word recognition. Our experiments show that the model is able to recognise words, and the gating paradigm reveals that words can be recognised from partial input as well and that recognition is negatively influenced by word competition from the word initial cohort.

Piotr Żelasko, Laureano Moro-Velázquez, Mark Hasegawa-Johnson et al.

Only a handful of the world's languages are abundant with the resources that enable practical applications of speech processing technologies. One of the methods to overcome this problem is to use the resources existing in other languages to train a multilingual automatic speech recognition (ASR) model, which, intuitively, should learn some universal phonetic representations. In this work, we focus on gaining a deeper understanding of how general these representations might be, and how individual phones are getting improved in a multilingual setting. To that end, we select a phonetically diverse set of languages, and perform a series of monolingual, multilingual and crosslingual (zero-shot) experiments. The ASR is trained to recognize the International Phonetic Alphabet (IPA) token sequences. We observe significant improvements across all languages in the multilingual setting, and stark degradation in the crosslingual setting, where the model, among other errors, considers Javanese as a tone language. Notably, as little as 10 hours of the target language training data tremendously reduces ASR error rates. Our analysis uncovered that even the phones that are unique to a single language can benefit greatly from adding training data from other languages - an encouraging result for the low-resource speech community.

Xinsheng Wang, Tingting Qiao, Jihua Zhu et al.

An estimated half of the world's languages do not have a written form, making it impossible for these languages to benefit from any existing text-based technologies. In this paper, a speech-to-image generation (S2IG) framework is proposed which translates speech descriptions to photo-realistic images without using any text information, thus allowing unwritten languages to potentially benefit from this technology. The proposed S2IG framework, named S2IGAN, consists of a speech embedding network (SEN) and a relation-supervised densely-stacked generative model (RDG). SEN learns the speech embedding with the supervision of the corresponding visual information. Conditioned on the speech embedding produced by SEN, the proposed RDG synthesizes images that are semantically consistent with the corresponding speech descriptions. Extensive experiments on two public benchmark datasets CUB and Oxford-102 demonstrate the effectiveness of the proposed S2IGAN on synthesizing high-quality and semantically-consistent images from the speech signal, yielding a good performance and a solid baseline for the S2IG task.

Odette Scharenborg, Martha Larson

Background music in social interaction settings can hinder conversation. Yet, little is known of how specific properties of music impact speech processing. This paper addresses this knowledge gap by investigating 1) whether the masking effect of background music with lyrics is larger than that of music without lyrics, and 2) whether the masking effect is larger for more complex music. To answer these questions, a word identification experiment was run in which Dutch participants listened to Dutch CVC words embedded in stretches of background music in two conditions, with and without lyrics, and at three SNRs. Three songs were used of different genres and complexities. Music stretches with and without lyrics were sampled from the same song in order to control for factors beyond the presence of lyrics. The results showed a clear negative impact of the presence of lyrics in background music on spoken-word recognition. This impact is independent of complexity. The results suggest that social spaces (e.g., restaurants, cafés and bars) should make careful choices of music to promote conversation, and open a path for future work.

Lucas Ondel, Pierre Godard, Laurent Besacier et al.

Developing speech technologies for low-resource languages has become a very active research field over the last decade. Among others, Bayesian models have shown some promising results on artificial examples but still lack of in situ experiments. Our work applies state-of-the-art Bayesian models to unsupervised Acoustic Unit Discovery (AUD) in a real low-resource language scenario. We also show that Bayesian models can naturally integrate information from other resourceful languages by means of informative prior leading to more consistent discovered units. Finally, discovered acoustic units are used, either as the 1-best sequence or as a lattice, to perform word segmentation. Word segmentation results show that this Bayesian approach clearly outperforms a Segmental-DTW baseline on the same corpus.

Odette Scharenborg, Laurent Besacier, Alan Black et al.

We summarize the accomplishments of a multi-disciplinary workshop exploring the computational and scientific issues surrounding the discovery of linguistic units (subwords and words) in a language without orthography. We study the replacement of orthographic transcriptions by images and/or translated text in a well-resourced language to help unsupervised discovery from raw speech.