arXiv subjects

Herman Kamper

Publications and source records attributed to Herman Kamper.

At least 55 records · Page 3Linked to original sources

arXiv2022

TransFusion: Transcribing Speech with Multinomial Diffusion

Diffusion models have shown exceptional scaling properties in the image synthesis domain, and initial attempts have shown similar benefits for applying diffusion to unconditional text synthesis. Denoising diffusion models attempt to iteratively refine a sampled noise signal until it resembles a coherent signal (such as an image or written sentence). In this work we aim to see whether the benefits of diffusion models can also be realized for speech recognition. To this end, we propose a new way to perform speech recognition using a diffusion model conditioned on pretrained speech features. Specifically, we propose TransFusion: a transcribing diffusion model which iteratively denoises a random character sequence into coherent text corresponding to the transcript of a conditioning utterance. We demonstrate comparable performance to existing high-performing contrastive models on the LibriSpeech speech recognition benchmark. To the best of our knowledge, we are the first to apply denoising diffusion to speech recognition. We also propose new techniques for effectively sampling and decoding multinomial diffusion models. These are required because traditional methods of sampling from acoustic models are not possible with our new discrete diffusion approach. Code and trained models are available: https://github.com/RF5/transfusion-asr

eess.AS↗

arXiv2022

YFACC: A Yorùbá speech-image dataset for cross-lingual keyword localisation through visual grounding

Visually grounded speech (VGS) models are trained on images paired with unlabelled spoken captions. Such models could be used to build speech systems in settings where it is impossible to get labelled data, e.g. for documenting unwritten languages. However, most VGS studies are in English or other high-resource languages. This paper attempts to address this shortcoming. We collect and release a new single-speaker dataset of audio captions for 6k Flickr images in Yorùbá -- a real low-resource language spoken in Nigeria. We train an attention-based VGS model where images are automatically tagged with English visual labels and paired with Yorùbá utterances. This enables cross-lingual keyword localisation: a written English query is detected and located in Yorùbá speech. To quantify the effect of the smaller dataset, we compare to English systems trained on similar and more data. We hope that this new dataset will stimulate research in the use of VGS models for real low-resource languages.

cs.CL↗

arXiv2022

Towards visually prompted keyword localisation for zero-resource spoken languages

Imagine being able to show a system a visual depiction of a keyword and finding spoken utterances that contain this keyword from a zero-resource speech corpus. We formalise this task and call it visually prompted keyword localisation (VPKL): given an image of a keyword, detect and predict where in an utterance the keyword occurs. To do VPKL, we propose a speech-vision model with a novel localising attention mechanism which we train with a new keyword sampling scheme. We show that these innovations give improvements in VPKL over an existing speech-vision model. We also compare to a visual bag-of-words (BoW) model where images are automatically tagged with visual labels and paired with unlabelled speech. Although this visual BoW can be queried directly with a written keyword (while our's takes image queries), our new model still outperforms the visual BoW in both detection and localisation, giving a 16% relative improvement in localisation F1.

cs.CL↗

arXiv2022

GAN You Hear Me? Reclaiming Unconditional Speech Synthesis from Diffusion Models

We propose AudioStyleGAN (ASGAN), a new generative adversarial network (GAN) for unconditional speech synthesis. As in the StyleGAN family of image synthesis models, ASGAN maps sampled noise to a disentangled latent vector which is then mapped to a sequence of audio features so that signal aliasing is suppressed at every layer. To successfully train ASGAN, we introduce a number of new techniques, including a modification to adaptive discriminator augmentation to probabilistically skip discriminator updates. ASGAN achieves state-of-the-art results in unconditional speech synthesis on the Google Speech Commands dataset. It is also substantially faster than the top-performing diffusion models. Through a design that encourages disentanglement, ASGAN is able to perform voice conversion and speech editing without being explicitly trained to do so. ASGAN demonstrates that GANs are still highly competitive with diffusion models. Code, models, samples: https://github.com/RF5/simple-asgan/.

cs.SD↗

arXiv2022

A Temporal Extension of Latent Dirichlet Allocation for Unsupervised Acoustic Unit Discovery

Latent Dirichlet allocation (LDA) is widely used for unsupervised topic modelling on sets of documents. No temporal information is used in the model. However, there is often a relationship between the corresponding topics of consecutive tokens. In this paper, we present an extension to LDA that uses a Markov chain to model temporal information. We use this new model for acoustic unit discovery from speech. As input tokens, the model takes a discretised encoding of speech from a vector quantised (VQ) neural network with 512 codes. The goal is then to map these 512 VQ codes to 50 phone-like units (topics) in order to more closely resemble true phones. In contrast to the base LDA, which only considers how VQ codes co-occur within utterances (documents), the Markov chain LDA additionally captures how consecutive codes follow one another. This extension leads to an increase in cluster quality and phone segmentation results compared to the base LDA. Compared to a recent vector quantised neural network approach that also learns 50 units, the extended LDA model performs better in phone segmentation but worse in mutual information.

eess.AS↗

arXiv2022

Voice Conversion Can Improve ASR in Very Low-Resource Settings

Voice conversion (VC) could be used to improve speech recognition systems in low-resource languages by using it to augment limited training data. However, VC has not been widely used for this purpose because of practical issues such as compute speed and limitations when converting to and from unseen speakers. Moreover, it is still unclear whether a VC model trained on one well-resourced language can be applied to speech from another low-resource language for the aim of data augmentation. In this work we assess whether a VC system can be used cross-lingually to improve low-resource speech recognition. We combine several recent techniques to design and train a practical VC system in English, and then use this system to augment data for training speech recognition models in several low-resource languages. When using a sensible amount of VC augmented data, speech recognition performance is improved in all four low-resource languages considered. We also show that VC-based augmentation is superior to SpecAugment (a widely used signal processing augmentation method) in the low-resource languages considered.

eess.AS↗

arXiv2022

A Comparison of Discrete and Soft Speech Units for Improved Voice Conversion

The goal of voice conversion is to transform source speech into a target voice, keeping the content unchanged. In this paper, we focus on self-supervised representation learning for voice conversion. Specifically, we compare discrete and soft speech units as input features. We find that discrete representations effectively remove speaker information but discard some linguistic content - leading to mispronunciations. As a solution, we propose soft speech units. To learn soft units, we predict a distribution over discrete speech units. By modeling uncertainty, soft units capture more content information, improving the intelligibility and naturalness of converted speech. Samples available at https://ubisoft-laforge.github.io/speech/soft-vc/. Code available at https://github.com/bshall/soft-vc/.

eess.AS↗

arXiv2022

Keyword localisation in untranscribed speech using visually grounded speech models

Keyword localisation is the task of finding where in a speech utterance a given query keyword occurs. We investigate to what extent keyword localisation is possible using a visually grounded speech (VGS) model. VGS models are trained on unlabelled images paired with spoken captions. These models are therefore self-supervised -- trained without any explicit textual label or location information. To obtain training targets, we first tag training images with soft text labels using a pretrained visual classifier with a fixed vocabulary. This enables a VGS model to predict the presence of a written keyword in an utterance, but not its location. We consider four ways to equip VGS models with localisations capabilities. Two of these -- a saliency approach and input masking -- can be applied to an arbitrary prediction model after training, while the other two -- attention and a score aggregation approach -- are incorporated directly into the structure of the model. Masked-based localisation gives some of the best reported localisation scores from a VGS model, with an accuracy of 57% when the system knows that a keyword occurs in an utterance and need to predict its location. In a setting where localisation is performed after detection, an $F_1$ of 25% is achieved, and in a setting where a keyword spotting ranking pass is first performed, we get a localisation P@10 of 32%. While these scores are modest compared to the idealised setting with unordered bag-of-word-supervision (from transcriptions), these models do not receive any textual or location supervision. Further analyses show that these models are limited by the first detection or ranking pass. Moreover, individual keyword localisation performance is correlated with the tagging performance from the visual classifier. We also show qualitatively how and where semantic mistakes occur, e.g. that the model locates surfer when queried with ocean.

cs.CL↗

arXiv2021

Feature learning for efficient ASR-free keyword spotting in low-resource languages

We consider feature learning for efficient keyword spotting that can be applied in severely under-resourced settings. The objective is to support humanitarian relief programmes by the United Nations in parts of Africa in which almost no language resources are available. For rapid development in such languages, we rely on a small, easily-compiled set of isolated keywords. These keyword templates are applied to a large corpus of in-domain but untranscribed speech using dynamic time warping (DTW). The resulting DTW alignment scores are used to train a convolutional neural network (CNN) which is orders of magnitude more computationally efficient and suitable for real-time application. We optimise this neural network keyword spotter by identifying robust acoustic features in this almost zero-resource setting. First, we incorporate information from well-resourced but unrelated languages using a multilingual bottleneck feature (BNF) extractor. Next, we consider features extracted from an autoencoder (AE) trained on in-domain but untranscribed data. Finally, we consider correspondence autoencoder (CAE) features which are fine-tuned on the small set of in-domain labelled data. Experiments in South African English and Luganda, a low-resource language, show that BNF and CAE features achieve a 5% relative performance improvement over baseline MFCCs. However, using BNFs as input to the CAE results in a more than 27% relative improvement over MFCCs in ROC area-under-the-curve (AUC) and more than twice as many top-10 retrievals. We show that, using these features, the CNN-DTW keyword spotter performs almost as well as the DTW keyword spotter while outperforming a baseline CNN trained only on the keyword templates. The CNN-DTW keyword spotter using BNF-derived CAE features represents an efficient approach with competitive performance suited to rapid deployment in a severely under-resourced scenario.

eess.AS↗

arXiv2021

Analyzing Speaker Information in Self-Supervised Models to Improve Zero-Resource Speech Processing

Contrastive predictive coding (CPC) aims to learn representations of speech by distinguishing future observations from a set of negative examples. Previous work has shown that linear classifiers trained on CPC features can accurately predict speaker and phone labels. However, it is unclear how the features actually capture speaker and phonetic information, and whether it is possible to normalize out the irrelevant details (depending on the downstream task). In this paper, we first show that the per-utterance mean of CPC features captures speaker information to a large extent. Concretely, we find that comparing means performs well on a speaker verification task. Next, probing experiments show that standardizing the features effectively removes speaker information. Based on this observation, we propose a speaker normalization step to improve acoustic unit discovery using K-means clustering of CPC features. Finally, we show that a language model trained on the resulting units achieves some of the best results in the ZeroSpeech2021~Challenge.

eess.AS↗

arXiv2021

Direct multimodal few-shot learning of speech and images

We propose direct multimodal few-shot models that learn a shared embedding space of spoken words and images from only a few paired examples. Imagine an agent is shown an image along with a spoken word describing the object in the picture, e.g. pen, book and eraser. After observing a few paired examples of each class, the model is asked to identify the "book" in a set of unseen pictures. Previous work used a two-step indirect approach relying on learned unimodal representations: speech-speech and image-image comparisons are performed across the support set of given speech-image pairs. We propose two direct models which instead learn a single multimodal space where inputs from different modalities are directly comparable: a multimodal triplet network (MTriplet) and a multimodal correspondence autoencoder (MCAE). To train these direct models, we mine speech-image pairs: the support set is used to pair up unlabelled in-domain speech and images. In a speech-to-image digit matching task, direct models outperform indirect models, with the MTriplet achieving the best multimodal five-shot accuracy. We show that the improvements are due to the combination of unsupervised and transfer learning in the direct models, and the absence of two-step compounding errors.

cs.CL↗

arXiv2021

Multilingual transfer of acoustic word embeddings improves when training on languages related to the target zero-resource language

Acoustic word embedding models map variable duration speech segments to fixed dimensional vectors, enabling efficient speech search and discovery. Previous work explored how embeddings can be obtained in zero-resource settings where no labelled data is available in the target language. The current best approach uses transfer learning: a single supervised multilingual model is trained using labelled data from multiple well-resourced languages and then applied to a target zero-resource language (without fine-tuning). However, it is still unclear how the specific choice of training languages affect downstream performance. Concretely, here we ask whether it is beneficial to use training languages related to the target. Using data from eleven languages spoken in Southern Africa, we experiment with adding data from different language families while controlling for the amount of data per language. In word discrimination and query-by-example search evaluations, we show that training on languages from the same family gives large improvements. Through finer-grained analysis, we show that training on even just a single related language gives the largest gain. We also find that adding data from unrelated languages generally doesn't hurt performance.

cs.CL↗

arXiv2021

Attention-Based Keyword Localisation in Speech using Visual Grounding

Visually grounded speech models learn from images paired with spoken captions. By tagging images with soft text labels using a trained visual classifier with a fixed vocabulary, previous work has shown that it is possible to train a model that can detect whether a particular text keyword occurs in speech utterances or not. Here we investigate whether visually grounded speech models can also do keyword localisation: predicting where, within an utterance, a given textual keyword occurs without any explicit text-based or alignment supervision. We specifically consider whether incorporating attention into a convolutional model is beneficial for localisation. Although absolute localisation performance with visually supervised models is still modest (compared to using unordered bag-of-word text labels for supervision), we show that attention provides a large gain in performance over previous visually grounded models. As in many other speech-image studies, we find that many of the incorrect localisations are due to semantic confusions, e.g. locating the word 'backstroke' for the query keyword 'swimming'.

cs.CL↗

arXiv2021

Towards unsupervised phone and word segmentation using self-supervised vector-quantized neural networks

We investigate segmenting and clustering speech into low-bitrate phone-like sequences without supervision. We specifically constrain pretrained self-supervised vector-quantized (VQ) neural networks so that blocks of contiguous feature vectors are assigned to the same code, thereby giving a variable-rate segmentation of the speech into discrete units. Two segmentation methods are considered. In the first, features are greedily merged until a prespecified number of segments are reached. The second uses dynamic programming to optimize a squared error with a penalty term to encourage fewer but longer segments. We show that these VQ segmentation methods can be used without alteration across a wide range of tasks: unsupervised phone segmentation, ABX phone discrimination, same-different word discrimination, and as inputs to a symbolic word segmentation algorithm. The penalized dynamic programming method generally performs best. While performance on individual tasks is only comparable to the state-of-the-art in some cases, in all tasks a reasonable competing approach is outperformed at a substantially lower bitrate.

cs.CL↗

arXiv2021

StarGAN-ZSVC: Towards Zero-Shot Voice Conversion in Low-Resource Contexts

Voice conversion is the task of converting a spoken utterance from a source speaker so that it appears to be said by a different target speaker while retaining the linguistic content of the utterance. Recent advances have led to major improvements in the quality of voice conversion systems. However, to be useful in a wider range of contexts, voice conversion systems would need to be (i) trainable without access to parallel data, (ii) work in a zero-shot setting where both the source and target speakers are unseen during training, and (iii) run in real time or faster. Recent techniques fulfil one or two of these requirements, but not all three. This paper extends recent voice conversion models based on generative adversarial networks (GANs), to satisfy all three of these conditions. We specifically extend the recent StarGAN-VC model by conditioning it on a speaker embedding (from a potentially unseen speaker). This allows the model to be used in a zero-shot setting, and we therefore call it StarGAN-ZSVC. We compare StarGAN-ZSVC against other voice conversion techniques in a low-resource setting using a small 9-minute training set. Compared to AutoVC -- another recent neural zero-shot approach -- we observe that StarGAN-ZSVC gives small improvements in the zero-shot setting, showing that real-time zero-shot voice conversion is possible even for a model trained on very little data. Further work is required to see whether scaling up StarGAN-ZSVC will also improve zero-shot voice conversion quality in high-resource contexts.

eess.AS↗

arXiv2021

Acoustic word embeddings for zero-resource languages using self-supervised contrastive learning and multilingual adaptation

Acoustic word embeddings (AWEs) are fixed-dimensional representations of variable-length speech segments. For zero-resource languages where labelled data is not available, one AWE approach is to use unsupervised autoencoder-based recurrent models. Another recent approach is to use multilingual transfer: a supervised AWE model is trained on several well-resourced languages and then applied to an unseen zero-resource language. We consider how a recent contrastive learning loss can be used in both the purely unsupervised and multilingual transfer settings. Firstly, we show that terms from an unsupervised term discovery system can be used for contrastive self-supervision, resulting in improvements over previous unsupervised monolingual AWE models. Secondly, we consider how multilingual AWE models can be adapted to a specific zero-resource language using discovered terms. We find that self-supervised contrastive adaptation outperforms adapted multilingual correspondence autoencoder and Siamese AWE models, giving the best overall results in a word discrimination task on six zero-resource languages.

cs.CL↗

arXiv2021

A phonetic model of non-native spoken word processing

Non-native speakers show difficulties with spoken word processing. Many studies attribute these difficulties to imprecise phonological encoding of words in the lexical memory. We test an alternative hypothesis: that some of these difficulties can arise from the non-native speakers' phonetic perception. We train a computational model of phonetic learning, which has no access to phonology, on either one or two languages. We first show that the model exhibits predictable behaviors on phone-level and word-level discrimination tasks. We then test the model on a spoken word processing task, showing that phonology may not be necessary to explain some of the word processing effects observed in non-native speakers. We run an additional analysis of the model's lexical representation space, showing that the two training languages are not fully separated in that space, similarly to the languages of a bilingual human speaker.

cs.CL↗

arXiv2021

Improved acoustic word embeddings for zero-resource languages using multilingual transfer

Acoustic word embeddings are fixed-dimensional representations of variable-length speech segments. Such embeddings can form the basis for speech search, indexing and discovery systems when conventional speech recognition is not possible. In zero-resource settings where unlabelled speech is the only available resource, we need a method that gives robust embeddings on an arbitrary language. Here we explore multilingual transfer: we train a single supervised embedding model on labelled data from multiple well-resourced languages and then apply it to unseen zero-resource languages. We consider three multilingual recurrent neural network (RNN) models: a classifier trained on the joint vocabularies of all training languages; a Siamese RNN trained to discriminate between same and different words from multiple languages; and a correspondence autoencoder (CAE) RNN trained to reconstruct word pairs. In a word discrimination task on six target languages, all of these models outperform state-of-the-art unsupervised models trained on the zero-resource languages themselves, giving relative improvements of more than 30% in average precision. When using only a few training languages, the multilingual CAE performs better, but with more training languages the other multilingual models perform similarly. Using more training languages is generally beneficial, but improvements are marginal on some languages. We present probing experiments which show that the CAE encodes more phonetic, word duration, language identity and speaker information than the other multilingual models.

cs.CL↗