The imitation of voice, targeted on specific speech attributes such as timbre and speaking style, is crucial in speech generation. However, existing methods rely heavily on annotated data, and struggle with effectively disentangling timbre and style, leading to challenges in achieving controllable generation, especially in zero-shot scenarios. To address these issues, we propose Vevo, a versatile zero-shot voice imitation framework with controllable timbre and style. Vevo operates in two core stages: (1) Content-Style Modeling: Given either text or speech's content tokens as input, we utilize an autoregressive transformer to generate the content-style tokens, which is prompted by a style reference; (2) Acoustic Modeling: Given the content-style tokens as input, we employ a flow-matching transformer to produce acoustic representations, which is prompted by a timbre reference. To obtain the content and content-style tokens of speech, we design a fully self-supervised approach that progressively decouples the timbre, style, and linguistic content of speech. Specifically, we adopt VQ-VAE as the tokenizer for the continuous hidden features of HuBERT. We treat the vocabulary size of the VQ-VAE codebook as the information bottleneck, and adjust it carefully to obtain the disentangled speech representations. Solely self-supervised trained on 60K hours of audiobook speech data, without any fine-tuning on style-specific corpora, Vevo matches or surpasses existing methods in accent and emotion conversion tasks. Additionally, Vevo’s effectiveness in zero-shot voice conversion and text-to-speech tasks further demonstrates its strong generalization and versatility. Audio samples are available at https://versavoice.github.io/.

Connectionist temporal classification (CTC) models are known to have peaky output distributions. Such behavior is not a problem for automatic speech recognition (ASR), but it can cause inaccurate forced alignments (FA), especially at finer granularity, e.g., phoneme level. This paper aims at alleviating the peaky behavior for CTC and improve its suitability for forced alignment generation, by leveraging label priors, so that the scores of alignment paths containing fewer blanks are boosted and maximized during training. As a result, our CTC model produces less peaky posteriors and is able to more accurately predict the offset of the tokens besides their onset. It outperforms the standard CTC model and a heuristics-based approach for obtaining CTC’s token offset timestamps by 12 − 40% in phoneme and word boundary errors (PBE and WBE) measured on the Buckeye and TIMIT data. Compared with the most widely used FA toolkit Montreal Forced Aligner (MFA), our method performs similarly on PBE/WBE on Buckeye, yet falls behind MFA on TIMIT. Nevertheless, our method has a much simpler training pipeline and better runtime efficiency. Our training recipe and pretrained model are released in TorchAudio.

A singing voice conversion model converts a song in the voice of an arbitrary source singer to the voice of a target singer. Recently, methods that leverage self-supervised audio representations such as HuBERT and Wav2Vec 2.0 have helped further the state-of-the-art. Though these methods produce more natural and melodic singing outputs, they often rely on confusion and disentanglement losses to render the self-supervised representations speaker and pitch-invariant. In this paper, we circumvent disentanglement training and propose a new model that leverages ASR fine-tuned self-supervised representations as inputs to a HiFi-GAN neural vocoder for singing voice conversion. We experiment with different f0encoding schemes and show that an f0harmonic generation module that uses a parallel bank of transposed convolutions (PBTC) alongside ASR fine-tuned Wav2Vec 2.0 features results in the best singing voice conversion quality. Additionally, the model is capable of making a spoken voice sing. We also show that a simple f0shifting scheme during inference helps retain singer identity and bolsters the performance of our singing voice conversion model. Our results are backed up by extensive MOS studies that compare different ablations and baselines.

Most people who have tried to learn a foreign language would have experienced difficulties understanding or speaking with a native speaker’s accent. For native speakers, understanding or speaking a new accent is likewise a difficult task. An accent conversion system that changes a speaker’s accent but preserves that speaker’s voice identity, such as timbre and pitch, has the potential for a range of applications, such as communication, language learning, and entertainment. Existing accent conversion models tend to change the speaker identity and accent at the same time. Here, we use adversarial learning to disentangle accent dependent features while retaining other acoustic characteristics. What sets our work apart from existing accent conversion models is the capability to convert an unseen speaker’s utterance to multiple accents while preserving its original voice identity. Subjective evaluations show that our model generates audio that sound closer to the target accent and like the original speaker.

Large-scale generative models such as GPT and DALL-E have revolutionized the research community. These models not only generate high fidelity outputs, but are also generalists which can solve tasks not explicitly taught. In contrast, speech generative models are still primitive in terms of scale and task generalization. In this paper, we present Voicebox, the most versatile text-guided generative model for speech at scale. Voicebox is a non-autoregressive flow-matching model trained to infill speech, given audio context and text, trained on over 50K hours of speech that are not filtered or enhanced. Similar to GPT, Voicebox can perform many different tasks through in-context learning, but is more flexible as it can also condition on future context. Voicebox can be used for mono or cross-lingual zero-shot text-to-speech synthesis, noise removal, content editing, style conversion, and diverse sample generation. In particular, Voicebox outperforms the state-of-the-art zero-shot TTS model VALL-E on both intelligibility (5.9\% vs 1.9\% word error rates) and audio similarity (0.580 vs 0.681) while being up to 20 times faster. Audio samples can be found in \url{https://voicebox.metademolab.com}.

In this paper, we introduce the Kaizen framework that uses a continuously improving teacher to generate pseudo-labels for semi-supervised speech recognition (ASR). The proposed approach uses a teacher model which is updated as the exponential moving average (EMA) of the student model parameters. We demonstrate that it is critical for EMA to be accumulated with full-precision floating point. The Kaizen framework can be seen as a continuous version of the iterative pseudo-labeling approach for semi-supervised training. It is applicable for different training criteria, and in this paper we demonstrate its effectiveness for frame-level hybrid hidden Markov model-deep neural network (HMM-DNN) systems as well as sequence-level Connectionist Temporal Classification (CTC) based models. For large scale real-world unsupervised public videos in UK English and Italian languages the proposed approach i) shows more than 10% relative word error rate (WER) reduction over standard teacher-student training; ii) using just 10 hours of supervised data and a large amount of unsupervised data closes the gap to the upper-bound supervised ASR system that uses 650h or 2700h respectively.

Hybrid automatic speech recognition (ASR) models are typically sequentially trained with CTC or LF-MMI criteria. However, they have vastly different legacies and are usually implemented in different frameworks. In this paper, by decoupling the concepts of modeling units and label topologies and building proper numerator/denominator graphs accordingly, we establish a generalized framework for hybrid acoustic modeling (AM). In this framework, we show that LF-MMI is a powerful training criterion applicable to both limited-context and full-context models, for wordpiece/mono-char/bi-char/chenone units, with both HMM/CTC topologies. From this framework, we propose three novel training schemes: chenone(ch)/wordpiece(wp)-CTC-bMMI, and wordpiece(wp)-HMM-bMMI with different advantages in training performance, decoding efficiency and decoding time-stamp accuracy. The advantages of different training schemes are evaluated comprehensively on Librispeech, and wp-CTC-bMMI and ch-CTC-bMMI are evaluated on two real world ASR tasks to show their effectiveness. Besides, we also show bi-char(bc) HMM-MMI models can serve as better alignment models than traditional non-neural GMM-HMMs.

Many semi- and weakly-supervised approaches have been investigated for overcoming the labeling cost of building high quality speech recognition systems. On the challenging task of transcribing social media videos in low-resource conditions, we conduct a large scale systematic comparison between two self-labeling methods on one hand, and weakly-supervised pretraining using contextual metadata on the other. We investigate distillation methods at the frame level and the sequence level for hybrid, encoder-only CTC-based, and encoder-decoder speech recognition systems on Dutch and Romanian languages using 27,000 and 58,000 hours of unlabeled audio respectively. Although all approaches improved upon their respective baseline WERs by more than 8%, sequence-level distillation for encoder-decoder models provided the largest relative WER reduction of 20% compared to the strongest data-augmented supervised baseline.

This paper summarizes our acoustic modeling efforts in the Johns Hopkins University speech recognition system for the CHiME-5 challenge to recognize highly-overlapped dinner party speech recorded by multiple microphone arrays. We explore data augmentation approaches, neural network architectures, front-end speech dereverberation, beamforming and robust i-vector extraction with comparisons of our in-house implementations and publicly available tools. We finally achieved a word error rate of 69.4% on the development set, which is a 11.7% absolute improvement over the previous baseline of 81.1%, and release this improved baseline with refined techniques/tools as an advanced CHiME-5 recipe.

This work explores different methods to detect errors in transcriptions of speech recordings. We artificially corrupt well transcribed speech transcriptions with three types of errors: substitution, insertion and deletion on TIMIT phonemic transcriptions and WSJ word transcriptions. First, we use Bayesian model selection method by comparing the log-likelihoods from alignment and phone recognizer, a final score is computed to make decision. In this method, we consider two models, Bayesian Hidden Markov Model (HMM) and a Variational Auto-Encoder (VAE) combined with a HMM. Alternately, we build a biased ASR system with language models trained on individual transcriptions, detection decision is based on Levenshtein distance (LD) between transcription and oracle path from decoded lattice. We evaluate the methods of detecting errors in corrupted TIMIT transcription, the best result (either using model selection with VAE model or biased ASR) achieves 7% equal error rate on the Detection Error Tradeoff (DET) curve; we also evaluate the methods of detecting errors in corrupted WSJ transcriptions, and the best result (using biased ASR) achieves 3% equal error rate.

Hybrid deep neural network hidden Markov models (DNN-HMM) have achieved impressive results on large vocabulary continuous speech recognition (LVCSR) tasks. However, the recent approaches using DNN-HMM models are not explored much for text recognition. Inspired by the current work in automatic speech recognition (ASR) and machine translation, we present an open vocabulary sub-word text recognition system. The sub-word lexicon and sub-word language model (LM) helps in overcoming the challenge of recognizing out of vocabulary (OOV) words, and a time delay neural network (TDNN) and convolution neural network (CNN) based DNN-HMM optical model (OM) efficiently models the sequence dependency in the line image. We present results on 12 datasets with training data varying from 6k lines to 600k lines. The system is built for 8 languages, i.e., English, French, Arabic, Chinese, Farsi, Tamil, Russian, and Korean. We report competitive results on several commonly used handwritten and printed text datasets.

To date, the bulk of research on speaker diarization has been conducted on telephone or near-field speech. As the need for technologies capable of handling conversational speech increases, it is necessary to establish the performance of state-of-the-art systems in this domain. In this work we evaluate the performance of an ivector/PLDA-based diarization system on the AMI Meeting Corpus, comparing performance on near-field, far-field, and signal-enhanced conditions.

The lattice-free MMI objective (LF-MMI) has been used in supervised training of state-of-the-art neural network acoustic models for automatic speech recognition (ASR). With large amounts of unsupervised data available, extending this approach to the semi-supervised scenario is of significance. Finite-state transducer (FST) based supervision used with LF-MMI provides a natural way to incorporate uncertainties when dealing with unsupervised data. In this paper, we describe various extensions to standard LF-MMI training to allow the use as supervision of lattices obtained via decoding of unsupervised data. The lattices are rescored with a strong LM. We investigate different methods for splitting the lattices and incorporating frame tolerances into the supervision FST. We report results on different subsets of Fisher English, where we achieve WER recovery of 59-64% using lattice supervision, which is significantly better than using just the best path transcription.

Teacher-student (T-S) learning is a transfer learning approach, where a teacher network is used to “teach” a student network to make the same predictions as the teacher. Originally formulated for model compression, this approach has also been used for domain adaptation, and is particularly effective when parallel data is available in source and target domains. The standard approach uses a frame-level objective of minimizing the KL divergence between the frame-level posteriors of the teacher and student networks. However, for sequence-trained models for speech recognition, it is more appropriate to train the student to mimic the sequence-level posterior of the teacher network. In this work, we compare this sequence-level KL divergence objective with another semi-supervised sequence-training method, namely the lattice-free MMI, for unsupervised domain adaptation. We investigate the approaches in multiple scenarios including adapting from clean to noisy speech, bandwidth mismatch and channel mismatch.

It is common in applications of ASR to have a large amount of data out-of-domain to the test data and a smaller amount of in-domain data similar to the test data. In this paper, we investigate different ways to utilize this out-of-domain data to improve ASR models based on Lattice-free MMI (LF-MMI). In particular, we experiment with multi-task training using a network with shared hidden layers; and we try various ways of adapting previously trained models to a new domain. Both types of methods are effective in reducing the WER versus in-domain models, with the jointly trained models generally giving more improvement.

This paper describes the JHU team's Kaldi system submission to the Arabic MGB-3: The Arabic speech recognition in the Wild Challenge for ASRU-2017. We use a weights transfer approach to adapt a neural network trained on the out-of-domain MGB-2 multi-dialect Arabic TV broadcast corpus to the MGB-3 Egyptian YouTube video corpus. The neural network has a TDNN-LSTM architecture and is trained using lattice-free maximum mutual information (LF-MMI) objective followed by sMBR discriminative training. For supervision, we fuse transcripts from 4 independent transcribers into confusion network training graphs. We also describe our own approach for speaker diarization and audio-transcript alignment. We use this to prepare lightly supervised transcriptions for training the seed system used for adaptation to MGB-3. Our primary submission to the challenge gives a multi-reference WER of 32.78% on the MGB-3 test set.

Speech recognition systems for irregularly-spelled languages like English normally require hand-written pronunciations.In this paper, we describe a system for automatically obtaining pronunciations of words for which pronunciations are not available, but for which transcribed data exists.Our method integrates information from the letter sequence and from the acoustic evidence.The novel aspect of the problem that we address is the problem of how to prune entries from such a lexicon (since, empirically, lexicons with too many entries do not tend to be good for ASR performance).Experiments on various ASR tasks show that, with the proposed framework, starting with an initial lexicon of several thousand words, we are able to learn a lexicon which performs close to a full expert lexicon in terms of WER performance on test data, and is better than lexicons built using G2P alone or with a pruning criterion based on pronunciation probability.

In many under-resourced languages it is possible to find text, and it is possible to find speech, but transcribed speech suitable for training automatic speech recognition (ASR) is unavailable. In the absence of native transcripts, this paper proposes the use of a probabilistic transcript: A probability mass function over possible phonetic transcripts of the waveform. Three sources of probabilistic transcripts are demonstrated. First, self-training is a well-established semisupervised learning technique, in which a cross-lingual ASR first labels unlabeled speech, and is then adapted using the same labels. Second, mismatched crowdsourcing is a recent technique in which nonspeakers of the language are asked to write what they hear, and their nonsense transcripts are decoded using noisy channel models of second-language speech perception. Third, EEG distribution coding is a new technique in which nonspeakers of the language listen to it, and their electrocortical response signals are interpreted to indicate probabilities. ASR was trained in four languages without native transcripts. Adaptation using mismatched crowdsourcing significantly outperformed self-training, and both significantly outperformed a cross-lingual baseline. Both EEG distribution coding and text-derived phone language models were shown to improve the quality of probabilistic transcripts derived from mismatched crowdsourcing.

Mismatched transcriptions of speech in a target language refers to transcriptions provided by people unfamiliar with the language, using English letter sequences. In this work, we demonstrate the value of such transcriptions in building an ASR system for the target language. For different languages, we use less than an hour of mismatched transcriptions to successfully adapt baseline multilingual models built with no access to native transcriptions in the target language. The adapted models provide up to 25% relative improvement in phone error rates on an unseen evaluation set.

Multi-style training, using data which emulates a variety of possible test scenarios, is a popular approach towards robust acoustic modeling. However acoustic models capable of exploiting large amounts of training data in a comparatively short amount of training time are essential. In this paper we tackle the problem of reverberant speech recognition using 5500 hours of simulated reverberant data. We use time-delay neural network (TDNN) architecture, which is capable of tackling long-term interactions between speech and corrupting sources in reverberant environments. By sub-sampling the outputs at TDNN layers across time steps, training time is substantially reduced. Combining this with distributed-optimization we show that the TDNN can be trained in 3 days using up to 32 GPUs. Further, iVectors are used as an input to the neural network to perform instantaneous speaker and environment adaptation. Finally, recurrent neural network language models are applied to the lattices to further improve the performance. Our system is shown to provide state-of-the-art results in the IARPA ASpIRE challenge, with 26.5% WER on the dev Jest set.

Maximum Mutual Information (MMI) is a popular discriminative criterion that has been used in supervised training of acoustic models for automatic speech recognition. However, standard discriminative training is very sensitive to the accuracy of the transcription and hence its implementation in a semisupervised setting requires extensive filtering of data. We will show that if the supervision transcripts are not known, the natural analogue of MMI is to minimize the conditional entropy of the lattice of possible transcripts of the data. This is equivalent to the weighted average of MMI criterion over different reference transcripts, taking those reference transcripts and their weighting from the lattice itself. In this paper we describe experiments where we applied this method to the semi-supervised training of Deep Neural Network acoustic models. In our experimental setup, the proposed method gives up to 0.5% absolute WER improvement over a DNN trained with sMBR only on the transcribed part of the data. This is 37% of the improvement that we would get from doing sMBR training if we had the transcripts for the untranscribed part of the data.

Provides an overview of a speech-to-text (STT) and keyword search (KWS) system architecture build primarily on the top of the Kaldi toolkit and expands on a few highlights. The system was developed as a part of the research efforts of the Radical team while participating in the IARPA Babel program. Our aim was to develop a general system pipeline which could be easily and rapidly deployed in any language, independently on the language script and phonological and linguistic features of the language.

In this paper, we propose a new acoustic modeling technique called the Phone-Cluster Adaptive Training. In this approach, the parameters of context-dependent states are obtained by the linear interpolation of several monophone cluster models, which are themselves obtained by adaptation using linear transformation of a canonical Gaussian Mixture Model (GMM). This approach is inspired from the Cluster Adaptive Training (CAT) for speaker adaptation and the Subspace Gaussian Mixture Model (SGMM). The parameters of the model are updated in an adaptive training framework. The interpolation vectors implicitly capture the phonetic context information. The proposed approach shows substantial improvement over the Continuous Density Hidden Markov Model (CDHMM) and a similar performance to that of the SGMM, while using significantly fewer parameters than both the CDHMM and the SGMM.