Korin Richmond

Jinzuomu Zhong, Yang Li, Hui Huang et al.

In expressive and controllable Text-to-Speech (TTS), explicit prosodic features significantly improve the naturalness and controllability of synthesised speech. However, manual prosody annotation is labor-intensive and inconsistent. To address this issue, a two-stage automatic annotation pipeline is novelly proposed in this paper. In the first stage, we use contrastive pretraining of Speech-Silence and Word-Punctuation (SSWP) pairs to enhance prosodic information in latent representations. In the second stage, we build a multi-modal prosody annotator, comprising pretrained encoders, a text-speech fusing scheme, and a sequence classifier. Experiments on English prosodic boundaries demonstrate that our method achieves state-of-the-art (SOTA) performance with 0.72 and 0.93 f1 score for Prosodic Word and Prosodic Phrase boundary respectively, while bearing remarkable robustness to data scarcity.

Cassia Valentini-Botinhao, Manuel Sam Ribeiro, Oliver Watts et al.

Automatically predicting the outcome of subjective listening tests is a challenging task. Ratings may vary from person to person even if preferences are consistent across listeners. While previous work has focused on predicting listeners' ratings (mean opinion scores) of individual stimuli, we focus on the simpler task of predicting subjective preference given two speech stimuli for the same text. We propose a model based on anti-symmetric twin neural networks, trained on pairs of waveforms and their corresponding preference scores. We explore both attention and recurrent neural nets to account for the fact that stimuli in a pair are not time aligned. To obtain a large training set we convert listeners' ratings from MUSHRA tests to values that reflect how often one stimulus in the pair was rated higher than the other. Specifically, we evaluate performance on data obtained from twelve MUSHRA evaluations conducted over five years, containing different TTS systems, built from data of different speakers. Our results compare favourably to a state-of-the-art model trained to predict MOS scores.

Jinzuomu Zhong, Korin Richmond, Zhiba Su et al.

While recent Zero-Shot Text-to-Speech (ZS-TTS) models have achieved high naturalness and speaker similarity, they fall short in accent fidelity and control. To address this issue, we propose zero-shot accent generation that unifies Foreign Accent Conversion (FAC), accented TTS, and ZS-TTS, with a novel two-stage pipeline. In the first stage, we achieve state-of-the-art (SOTA) on Accent Identification (AID) with 0.56 f1 score on unseen speakers. In the second stage, we condition a ZS-TTS system on the pretrained speaker-agnostic accent embeddings extracted by the AID model. The proposed system achieves higher accent fidelity on inherent/cross accent generation, and enables unseen accent generation.

Yujia Sun, Zeyu Zhao, Korin Richmond et al.

Emotion recognition from speech and music shares similarities due to their acoustic overlap, which has led to interest in transferring knowledge between these domains. However, the shared acoustic cues between speech and music, particularly those encoded by Self-Supervised Learning (SSL) models, remain largely unexplored, given the fact that SSL models for speech and music have rarely been applied in cross-domain research. In this work, we revisit the acoustic similarity between emotion speech and music, starting with an analysis of the layerwise behavior of SSL models for Speech Emotion Recognition (SER) and Music Emotion Recognition (MER). Furthermore, we perform cross-domain adaptation by comparing several approaches in a two-stage fine-tuning process, examining effective ways to utilize music for SER and speech for MER. Lastly, we explore the acoustic similarities between emotional speech and music using Frechet audio distance for individual emotions, uncovering the issue of emotion bias in both speech and music SSL models. Our findings reveal that while speech and music SSL models do capture shared acoustic features, their behaviors can vary depending on different emotions due to their training strategies and domain-specificities. Additionally, parameter-efficient fine-tuning can enhance SER and MER performance by leveraging knowledge from each other. This study provides new insights into the acoustic similarity between emotional speech and music, and highlights the potential for cross-domain generalization to improve SER and MER systems.

Ingmar Steiner, Korin Richmond, Slim Ouni

Electromagnetic articulography (EMA) captures the position and orientation of a number of markers, attached to the articulators, during speech. As such, it performs the same function for speech that conventional motion capture does for full-body movements acquired with optical modalities, a long-time staple technique of the animation industry. In this paper, EMA data is processed from a motion-capture perspective and applied to the visualization of an existing multimodal corpus of articulatory data, creating a kinematic 3D model of the tongue and teeth by adapting a conventional motion capture based animation paradigm. This is accomplished using off-the-shelf, open-source software. Such an animated model can then be easily integrated into multimedia applications as a digital asset, allowing the analysis of speech production in an intuitive and accessible manner. The processing of the EMA data, its co-registration with 3D data from vocal tract magnetic resonance imaging (MRI) and dental scans, and the modeling workflow are presented in detail, and several issues discussed.

Zhichen Han, Tianqi Geng, Hui Feng et al.

Utilizing Self-Supervised Learning (SSL) models for Speech Emotion Recognition (SER) has proven effective, yet limited research has explored cross-lingual scenarios. This study presents a comparative analysis between human performance and SSL models, beginning with a layer-wise analysis and an exploration of parameter-efficient fine-tuning strategies in monolingual, cross-lingual, and transfer learning contexts. We further compare the SER ability of models and humans at both utterance- and segment-levels. Additionally, we investigate the impact of dialect on cross-lingual SER through human evaluation. Our findings reveal that models, with appropriate knowledge transfer, can adapt to the target language and achieve performance comparable to native speakers. We also demonstrate the significant effect of dialect on SER for individuals without prior linguistic and paralinguistic background. Moreover, both humans and models exhibit distinct behaviors across different emotions. These results offer new insights into the cross-lingual SER capabilities of SSL models, underscoring both their similarities to and differences from human emotion perception.

Jinzuomu Zhong, Yi Wang, Korin Richmond et al.

Discrete Speech Representation Tokens (DSRTs) have become a foundational component in speech generation. While prior work has extensively studied phonetic and speaker information in DSRTs, how accent information is encoded in DSRTs remains largely unexplored. In this paper, we present the first systematic investigation of accent information in DSRTs. We propose a unified evaluation framework that measures both accessibility of accent information via a novel Accent ABX task and recoverability via cross-accent Voice Conversion (VC) resynthesis. Using this framework, we analyse DSRTs derived from a variety of speech encoders. Our results reveal that accent information is substantially reduced when ASR supervision is used to fine-tune the encoder, but cannot be effectively disentangled from phonetic and speaker information through naive codebook size reduction. Based on these findings, we propose new content-only and content-accent DSRTs that significantly outperform existing designs in controllable accent generation. Our work highlights the importance of accent-aware evaluation and provides practical guidance for designing DSRTs for accent-controlled speech generation.

Siqi Sun, Korin Richmond

Recent work has shown the feasibility and benefit of bootstrapping an integrated sequence-to-sequence (Seq2Seq) linguistic frontend from a traditional pipeline-based frontend for text-to-speech (TTS). To overcome the fixed lexical coverage of bootstrapping training data, previous work has proposed to leverage easily accessible transcribed speech audio as an additional training source for acquiring novel pronunciation knowledge for uncovered words, which relies on an auxiliary ASR model as part of a cumbersome implementation flow. In this work, we propose an alternative method to leverage transcribed speech audio as an additional training source, based on multi-task learning (MTL). Experiments show that, compared to a baseline Seq2Seq frontend, the proposed MTL-based method reduces PER from 2.5% to 1.6% for those word types covered exclusively in transcribed speech audio, achieving a similar performance to the previous method but with a much simpler implementation flow.

Jinzuomu Zhong, Suyuan Liu, Dan Wells et al.

Despite growing interest in generating high-fidelity accents, evaluating accent similarity in speech synthesis has been underexplored. We aim to enhance both subjective and objective evaluation methods for accent similarity. Subjectively, we refine the XAB listening test by adding components that achieve higher statistical significance with fewer listeners and lower costs. Our method involves providing listeners with transcriptions, having them highlight perceived accent differences, and implementing meticulous screening for reliability. Objectively, we utilise pronunciation-related metrics, based on distances between vowel formants and phonetic posteriorgrams, to evaluate accent generation. Comparative experiments reveal that these metrics, alongside accent similarity, speaker similarity, and Mel Cepstral Distortion, can be used. Moreover, our findings underscore significant limitations of common metrics like Word Error Rate in assessing underrepresented accents.

Nicholas Sanders, Yuanchao Li, Korin Richmond et al.

Quantization in SSL speech models (e.g., HuBERT) improves compression and performance in tasks like language modeling, resynthesis, and text-to-speech but often discards prosodic and paralinguistic information (e.g., emotion, prominence). While increasing codebook size mitigates some loss, it inefficiently raises bitrates. We propose Segmentation-Variant Codebooks (SVCs), which quantize speech at distinct linguistic units (frame, phone, word, utterance), factorizing it into multiple streams of segment-specific discrete features. Our results show that SVCs are significantly more effective at preserving prosodic and paralinguistic information across probing tasks. Additionally, we find that pooling before rather than after discretization better retains segment-level information. Resynthesis experiments further confirm improved style realization and slightly improved quality while preserving intelligibility.

Cheng Gong, Erica Cooper, Xin Wang et al.

Self-supervised learning (SSL) representations from massively multilingual models offer a promising solution for low-resource language speech tasks. Despite advancements, language adaptation in TTS systems remains an open problem. This paper explores the language adaptation capability of ZMM-TTS, a recent SSL-based multilingual TTS system proposed in our previous work. We conducted experiments on 12 languages using limited data with various fine-tuning configurations. We demonstrate that the similarity in phonetics between the pre-training and target languages, as well as the language category, affects the target language's adaptation performance. Additionally, we find that the fine-tuning dataset size and number of speakers influence adaptability. Surprisingly, we also observed that using paired data for fine-tuning is not always optimal compared to audio-only data. Beyond speech intelligibility, our analysis covers speaker similarity, language identification, and predicted MOS.

Aciel Eshky, Joanne Cleland, Manuel Sam Ribeiro et al.

Ultrasound tongue imaging is used to visualise the intra-oral articulators during speech production. It is utilised in a range of applications, including speech and language therapy and phonetics research. Ultrasound and speech audio are recorded simultaneously, and in order to correctly use this data, the two modalities should be correctly synchronised. Synchronisation is achieved using specialised hardware at recording time, but this approach can fail in practice resulting in data of limited usability. In this paper, we address the problem of automatically synchronising ultrasound and audio after data collection. We first investigate the tolerance of expert ultrasound users to synchronisation errors in order to find the thresholds for error detection. We use these thresholds to define accuracy scoring boundaries for evaluating our system. We then describe our approach for automatic synchronisation, which is driven by a self-supervised neural network, exploiting the correlation between the two signals to synchronise them. We train our model on data from multiple domains with different speaker characteristics, different equipment, and different recording environments, and achieve an accuracy >92.4% on held-out in-domain data. Finally, we introduce a novel resource, the Cleft dataset, which we gathered with a new clinical subgroup and for which hardware synchronisation proved unreliable. We apply our model to this out-of-domain data, and evaluate its performance subjectively with expert users. Results show that users prefer our model's output over the original hardware output 79.3% of the time. Our results demonstrate the strength of our approach and its ability to generalise to data from new domains.

Manuel Sam Ribeiro, Aciel Eshky, Korin Richmond et al.

We investigate multi-speaker speech recognition from ultrasound images of the tongue and video images of the lips. We train our systems on imaging data from modal speech, and evaluate on matched test sets of two speaking modes: silent and modal speech. We observe that silent speech recognition from imaging data underperforms compared to modal speech recognition, likely due to a speaking-mode mismatch between training and testing. We improve silent speech recognition performance using techniques that address the domain mismatch, such as fMLLR and unsupervised model adaptation. We also analyse the properties of silent and modal speech in terms of utterance duration and the size of the articulatory space. To estimate the articulatory space, we compute the convex hull of tongue splines, extracted from ultrasound tongue images. Overall, we observe that the duration of silent speech is longer than that of modal speech, and that silent speech covers a smaller articulatory space than modal speech. Although these two properties are statistically significant across speaking modes, they do not directly correlate with word error rates from speech recognition.

Manuel Sam Ribeiro, Joanne Cleland, Aciel Eshky et al.

Speech sound disorders are a common communication impairment in childhood. Because speech disorders can negatively affect the lives and the development of children, clinical intervention is often recommended. To help with diagnosis and treatment, clinicians use instrumented methods such as spectrograms or ultrasound tongue imaging to analyse speech articulations. Analysis with these methods can be laborious for clinicians, therefore there is growing interest in its automation. In this paper, we investigate the contribution of ultrasound tongue imaging for the automatic detection of speech articulation errors. Our systems are trained on typically developing child speech and augmented with a database of adult speech using audio and ultrasound. Evaluation on typically developing speech indicates that pre-training on adult speech and jointly using ultrasound and audio gives the best results with an accuracy of 86.9%. To evaluate on disordered speech, we collect pronunciation scores from experienced speech and language therapists, focusing on cases of velar fronting and gliding of /r/. The scores show good inter-annotator agreement for velar fronting, but not for gliding errors. For automatic velar fronting error detection, the best results are obtained when jointly using ultrasound and audio. The best system correctly detects 86.6% of the errors identified by experienced clinicians. Out of all the segments identified as errors by the best system, 73.2% match errors identified by clinicians. Results on automatic gliding detection are harder to interpret due to poor inter-annotator agreement, but appear promising. Overall findings suggest that automatic detection of speech articulation errors has potential to be integrated into ultrasound intervention software for automatically quantifying progress during speech therapy.

Manuel Sam Ribeiro, Jennifer Sanger, Jing-Xuan Zhang et al.

We present the Tongue and Lips corpus (TaL), a multi-speaker corpus of audio, ultrasound tongue imaging, and lip videos. TaL consists of two parts: TaL1 is a set of six recording sessions of one professional voice talent, a male native speaker of English; TaL80 is a set of recording sessions of 81 native speakers of English without voice talent experience. Overall, the corpus contains 24 hours of parallel ultrasound, video, and audio data, of which approximately 13.5 hours are speech. This paper describes the corpus and presents benchmark results for the tasks of speech recognition, speech synthesis (articulatory-to-acoustic mapping), and automatic synchronisation of ultrasound to audio. The TaL corpus is publicly available under the CC BY-NC 4.0 license.

Aciel Eshky, Manuel Sam Ribeiro, Joanne Cleland et al.

We introduce UltraSuite, a curated repository of ultrasound and acoustic data, collected from recordings of child speech therapy sessions. This release includes three data collections, one from typically developing children and two from children with speech sound disorders. In addition, it includes a set of annotations, some manual and some automatically produced, and software tools to process, transform and visualise the data.

Manuel Sam Ribeiro, Aciel Eshky, Korin Richmond et al.

We investigate the automatic processing of child speech therapy sessions using ultrasound visual biofeedback, with a specific focus on complementing acoustic features with ultrasound images of the tongue for the tasks of speaker diarization and time-alignment of target words. For speaker diarization, we propose an ultrasound-based time-domain signal which we call estimated tongue activity. For word-alignment, we augment an acoustic model with low-dimensional representations of ultrasound images of the tongue, learned by a convolutional neural network. We conduct our experiments using the Ultrasuite repository of ultrasound and speech recordings for child speech therapy sessions. For both tasks, we observe that systems augmented with ultrasound data outperform corresponding systems using only the audio signal.

Aciel Eshky, Manuel Sam Ribeiro, Korin Richmond et al.

Audiovisual synchronisation is the task of determining the time offset between speech audio and a video recording of the articulators. In child speech therapy, audio and ultrasound videos of the tongue are captured using instruments which rely on hardware to synchronise the two modalities at recording time. Hardware synchronisation can fail in practice, and no mechanism exists to synchronise the signals post hoc. To address this problem, we employ a two-stream neural network which exploits the correlation between the two modalities to find the offset. We train our model on recordings from 69 speakers, and show that it correctly synchronises 82.9% of test utterances from unseen therapy sessions and unseen speakers, thus considerably reducing the number of utterances to be manually synchronised. An analysis of model performance on the test utterances shows that directed phone articulations are more difficult to automatically synchronise compared to utterances containing natural variation in speech such as words, sentences, or conversations.

Manuel Sam Ribeiro, Aciel Eshky, Korin Richmond et al.

Ultrasound tongue imaging (UTI) provides a convenient way to visualize the vocal tract during speech production. UTI is increasingly being used for speech therapy, making it important to develop automatic methods to assist various time-consuming manual tasks currently performed by speech therapists. A key challenge is to generalize the automatic processing of ultrasound tongue images to previously unseen speakers. In this work, we investigate the classification of phonetic segments (tongue shapes) from raw ultrasound recordings under several training scenarios: speaker-dependent, multi-speaker, speaker-independent, and speaker-adapted. We observe that models underperform when applied to data from speakers not seen at training time. However, when provided with minimal additional speaker information, such as the mean ultrasound frame, the models generalize better to unseen speakers.

Cheng-I Lai, Alberto Abad, Korin Richmond et al.

An attacker may use a variety of techniques to fool an automatic speaker verification system into accepting them as a genuine user. Anti-spoofing methods meanwhile aim to make the system robust against such attacks. The ASVspoof 2017 Challenge focused specifically on replay attacks, with the intention of measuring the limits of replay attack detection as well as developing countermeasures against them. In this work, we propose our replay attacks detection system - Attentive Filtering Network, which is composed of an attention-based filtering mechanism that enhances feature representations in both the frequency and time domains, and a ResNet-based classifier. We show that the network enables us to visualize the automatically acquired feature representations that are helpful for spoofing detection. Attentive Filtering Network attains an evaluation EER of 8.99$\%$ on the ASVspoof 2017 Version 2.0 dataset. With system fusion, our best system further obtains a 30$\%$ relative improvement over the ASVspoof 2017 enhanced baseline system.

Alexander Hewer, Stefanie Wuhrer, Ingmar Steiner et al.

We present a multilinear statistical model of the human tongue that captures anatomical and tongue pose related shape variations separately. The model is derived from 3D magnetic resonance imaging data of 11 speakers sustaining speech related vocal tract configurations. The extraction is performed by using a minimally supervised method that uses as basis an image segmentation approach and a template fitting technique. Furthermore, it uses image denoising to deal with possibly corrupt data, palate surface information reconstruction to handle palatal tongue contacts, and a bootstrap strategy to refine the obtained shapes. Our evaluation concludes that limiting the degrees of freedom for the anatomical and speech related variations to 5 and 4, respectively, produces a model that can reliably register unknown data while avoiding overfitting effects. Furthermore, we show that it can be used to generate a plausible tongue animation by tracking sparse motion capture data.

Alexander Hewer, Ingmar Steiner, Timo Bolkart et al.

We describe a minimally-supervised method for computing a statistical shape space model of the palate surface. The model is created from a corpus of volumetric magnetic resonance imaging (MRI) scans collected from 12 speakers. We extract a 3D mesh of the palate from each speaker, then train the model using principal component analysis (PCA). The palate model is then tested using 3D MRI from another corpus and evaluated using a high-resolution optical scan. We find that the error is low even when only a handful of measured coordinates are available. In both cases, our approach yields promising results. It can be applied to extract the palate shape from MRI data, and could be useful to other analysis modalities, such as electromagnetic articulography (EMA) and ultrasound tongue imaging (UTI).

Ingmar Steiner, Korin Richmond, Slim Ouni

The importance of modeling speech articulation for high-quality audiovisual (AV) speech synthesis is widely acknowledged. Nevertheless, while state-of-the-art, data-driven approaches to facial animation can make use of sophisticated motion capture techniques, the animation of the intraoral articulators (viz. the tongue, jaw, and velum) typically makes use of simple rules or viseme morphing, in stark contrast to the otherwise high quality of facial modeling. Using appropriate speech production data could significantly improve the quality of articulatory animation for AV synthesis.