arXiv subjects

Joseph Keshet

Publications and source records attributed to Joseph Keshet.

At least 37 records · Page 2Linked to original sources

arXiv2025

UmbraTTS: Adapting Text-to-Speech to Environmental Contexts with Flow Matching

Recent advances in Text-to-Speech (TTS) have enabled highly natural speech synthesis, yet integrating speech with complex background environments remains challenging. We introduce UmbraTTS, a flow-matching based TTS model that jointly generates both speech and environmental audio, conditioned on text and acoustic context. Our model allows fine-grained control over background volume and produces diverse, coherent, and context-aware audio scenes. A key challenge is the lack of data with speech and background audio aligned in natural context. To overcome the lack of paired training data, we propose a self-supervised framework that extracts speech, background audio, and transcripts from unannotated recordings. Extensive evaluations demonstrate that UmbraTTS significantly outperformed existing baselines, producing natural, high-quality, environmentally aware audios.

cs.SD↗

arXiv2025

FlowTSE: Target Speaker Extraction with Flow Matching

Target speaker extraction (TSE) aims to isolate a specific speaker's speech from a mixture using speaker enrollment as a reference. While most existing approaches are discriminative, recent generative methods for TSE achieve strong results. However, generative methods for TSE remain underexplored, with most existing approaches relying on complex pipelines and pretrained components, leading to computational overhead. In this work, we present FlowTSE, a simple yet effective TSE approach based on conditional flow matching. Our model receives an enrollment audio sample and a mixed speech signal, both represented as mel-spectrograms, with the objective of extracting the target speaker's clean speech. Furthermore, for tasks where phase reconstruction is crucial, we propose a novel vocoder conditioned on the complex STFT of the mixed signal, enabling improved phase estimation. Experimental results on standard TSE benchmarks show that FlowTSE matches or outperforms strong baselines.

eess.AS↗

arXiv2024

Whisper in Medusa's Ear: Multi-head Efficient Decoding for Transformer-based ASR

Large transformer-based models have significant potential for speech transcription and translation. Their self-attention mechanisms and parallel processing enable them to capture complex patterns and dependencies in audio sequences. However, this potential comes with challenges, as these large and computationally intensive models lead to slow inference speeds. Various optimization strategies have been proposed to improve performance, including efficient hardware utilization and algorithmic enhancements. In this paper, we introduce Whisper-Medusa, a novel approach designed to enhance processing speed with minimal impact on Word Error Rate (WER). The proposed model extends the OpenAI's Whisper architecture by predicting multiple tokens per iteration, resulting in a 50% reduction in latency. We showcase the effectiveness of Whisper-Medusa across different learning setups and datasets.

eess.AS↗

arXiv2024

HebDB: a Weakly Supervised Dataset for Hebrew Speech Processing

We present HebDB, a weakly supervised dataset for spoken language processing in the Hebrew language. HebDB offers roughly 2500 hours of natural and spontaneous speech recordings in the Hebrew language, consisting of a large variety of speakers and topics. We provide raw recordings together with a pre-processed, weakly supervised, and filtered version. The goal of HebDB is to further enhance research and development of spoken language processing tools for the Hebrew language. Hence, we additionally provide two baseline systems for Automatic Speech Recognition (ASR): (i) a self-supervised model; and (ii) a fully supervised model. We present the performance of these two methods optimized on HebDB and compare them to current multi-lingual ASR alternatives. Results suggest the proposed method reaches better results than the evaluated baselines considering similar model sizes. Dataset, code, and models are publicly available under https://pages.cs.huji.ac.il/adiyoss-lab/HebDB/.

cs.CL↗

arXiv2024

Enhanced ASR Robustness to Packet Loss with a Front-End Adaptation Network

In the realm of automatic speech recognition (ASR), robustness in noisy environments remains a significant challenge. Recent ASR models, such as Whisper, have shown promise, but their efficacy in noisy conditions can be further enhanced. This study is focused on recovering from packet loss to improve the word error rate (WER) of ASR models. We propose using a front-end adaptation network connected to a frozen ASR model. The adaptation network is trained to modify the corrupted input spectrum by minimizing the criteria of the ASR model in addition to an enhancement loss function. Our experiments demonstrate that the adaptation network, trained on Whisper's criteria, notably reduces word error rates across domains and languages in packet-loss scenarios. This improvement is achieved with minimal affect to Whisper model's foundational performance, underscoring our method's practicality and potential in enhancing ASR models in challenging acoustic environments.

cs.SD↗

arXiv2024

Tradition or Innovation: A Comparison of Modern ASR Methods for Forced Alignment

Forced alignment (FA) plays a key role in speech research through the automatic time alignment of speech signals with corresponding text transcriptions. Despite the move towards end-to-end architectures for speech technology, FA is still dominantly achieved through a classic GMM-HMM acoustic model. This work directly compares alignment performance from leading automatic speech recognition (ASR) methods, WhisperX and Massively Multilingual Speech Recognition (MMS), against a Kaldi-based GMM-HMM system, the Montreal Forced Aligner (MFA). Performance was assessed on the manually aligned TIMIT and Buckeye datasets, with comparisons conducted only on words correctly recognized by WhisperX and MMS. The MFA outperformed both WhisperX and MMS, revealing a shortcoming of modern ASR systems. These findings highlight the need for advancements in forced alignment and emphasize the importance of integrating traditional expertise with modern innovation to foster progress. Index Terms: forced alignment, phoneme alignment, word alignment

eess.AS↗

arXiv2024

Keyword-Guided Adaptation of Automatic Speech Recognition

Automatic Speech Recognition (ASR) technology has made significant progress in recent years, providing accurate transcription across various domains. However, some challenges remain, especially in noisy environments and specialized jargon. In this paper, we propose a novel approach for improved jargon word recognition by contextual biasing Whisper-based models. We employ a keyword spotting model that leverages the Whisper encoder representation to dynamically generate prompts for guiding the decoder during the transcription process. We introduce two approaches to effectively steer the decoder towards these prompts: KG-Whisper, which is aimed at fine-tuning the Whisper decoder, and KG-Whisper-PT, which learns a prompt prefix. Our results show a significant improvement in the recognition accuracy of specified keywords and in reducing the overall word error rates. Specifically, in unseen language generalization, we demonstrate an average WER improvement of 5.1% over Whisper.

eess.AS↗

arXiv2024

DiffAR: Denoising Diffusion Autoregressive Model for Raw Speech Waveform Generation

Diffusion models have recently been shown to be relevant for high-quality speech generation. Most work has been focused on generating spectrograms, and as such, they further require a subsequent model to convert the spectrogram to a waveform (i.e., a vocoder). This work proposes a diffusion probabilistic end-to-end model for generating a raw speech waveform. The proposed model is autoregressive, generating overlapping frames sequentially, where each frame is conditioned on a portion of the previously generated one. Hence, our model can effectively synthesize an unlimited speech duration while preserving high-fidelity synthesis and temporal coherence. We implemented the proposed model for unconditional and conditional speech generation, where the latter can be driven by an input sequence of phonemes, amplitudes, and pitch values. Working on the waveform directly has some empirical advantages. Specifically, it allows the creation of local acoustic behaviors, like vocal fry, which makes the overall waveform sounds more natural. Furthermore, the proposed diffusion model is stochastic and not deterministic; therefore, each inference generates a slightly different waveform variation, enabling abundance of valid realizations. Experiments show that the proposed model generates speech with superior quality compared with other state-of-the-art neural speech generation systems.

cs.SD↗

arXiv2023

Combining Language Models For Specialized Domains: A Colorful Approach

General purpose language models (LMs) encounter difficulties when processing domain-specific jargon and terminology, which are frequently utilized in specialized fields such as medicine or industrial settings. Moreover, they often find it challenging to interpret mixed speech that blends general language with specialized jargon. This poses a challenge for automatic speech recognition systems operating within these specific domains. In this work, we introduce a novel approach that integrates domain-specific or secondary LM into general-purpose LM. This strategy involves labeling, or "coloring", each word to indicate its association with either the general or the domain-specific LM. We develop an optimized algorithm that enhances the beam search algorithm to effectively handle inferences involving colored words. Our evaluations indicate that this approach is highly effective in integrating jargon into language tasks. Notably, our method substantially lowers the error rate for domain-specific words without compromising performance in the general domain.

cs.CL↗

arXiv2023

Open-vocabulary Keyword-spotting with Adaptive Instance Normalization

Open vocabulary keyword spotting is a crucial and challenging task in automatic speech recognition (ASR) that focuses on detecting user-defined keywords within a spoken utterance. Keyword spotting methods commonly map the audio utterance and keyword into a joint embedding space to obtain some affinity score. In this work, we propose AdaKWS, a novel method for keyword spotting in which a text encoder is trained to output keyword-conditioned normalization parameters. These parameters are used to process the auditory input. We provide an extensive evaluation using challenging and diverse multi-lingual benchmarks and show significant improvements over recent keyword spotting and ASR baselines. Furthermore, we study the effectiveness of our approach on low-resource languages that were unseen during the training. The results demonstrate a substantial performance improvement compared to baseline methods.

eess.AS↗

arXiv2022

A Baseline for Detecting Out-of-Distribution Examples in Image Captioning

Image captioning research achieved breakthroughs in recent years by developing neural models that can generate diverse and high-quality descriptions for images drawn from the same distribution as training images. However, when facing out-of-distribution (OOD) images, such as corrupted images, or images containing unknown objects, the models fail in generating relevant captions. In this paper, we consider the problem of OOD detection in image captioning. We formulate the problem and suggest an evaluation setup for assessing the model's performance on the task. Then, we analyze and show the effectiveness of the caption's likelihood score at detecting and rejecting OOD images, which implies that the relatedness between the input image and the generated caption is encapsulated within the score.

cs.CV↗

arXiv2022

Correcting Mispronunciations in Speech using Spectrogram Inpainting

Learning a new language involves constantly comparing speech productions with reference productions from the environment. Early in speech acquisition, children make articulatory adjustments to match their caregivers' speech. Grownup learners of a language tweak their speech to match the tutor reference. This paper proposes a method to synthetically generate correct pronunciation feedback given incorrect production. Furthermore, our aim is to generate the corrected production while maintaining the speaker's original voice. The system prompts the user to pronounce a phrase. The speech is recorded, and the samples associated with the inaccurate phoneme are masked with zeros. This waveform serves as an input to a speech generator, implemented as a deep learning inpainting system with a U-net architecture, and trained to output a reconstructed speech. The training set is composed of unimpaired proper speech examples, and the generator is trained to reconstruct the original proper speech. We evaluated the performance of our system on phoneme replacement of minimal pair words of English as well as on children with pronunciation disorders. Results suggest that human listeners slightly prefer our generated speech over a smoothed replacement of the inaccurate phoneme with a production of a different speaker.

eess.AS↗

arXiv2022

DDKtor: Automatic Diadochokinetic Speech Analysis

Diadochokinetic speech tasks (DDK), in which participants repeatedly produce syllables, are commonly used as part of the assessment of speech motor impairments. These studies rely on manual analyses that are time-intensive, subjective, and provide only a coarse-grained picture of speech. This paper presents two deep neural network models that automatically segment consonants and vowels from unannotated, untranscribed speech. Both models work on the raw waveform and use convolutional layers for feature extraction. The first model is based on an LSTM classifier followed by fully connected layers, while the second model adds more convolutional layers followed by fully connected layers. These segmentations predicted by the models are used to obtain measures of speech rate and sound duration. Results on a young healthy individuals dataset show that our LSTM model outperforms the current state-of-the-art systems and performs comparably to trained human annotators. Moreover, the LSTM model also presents comparable results to trained human annotators when evaluated on unseen older individuals with Parkinson's Disease dataset.

eess.AS↗

arXiv2022

DeepFry: Identifying Vocal Fry Using Deep Neural Networks

Vocal fry or creaky voice refers to a voice quality characterized by irregular glottal opening and low pitch. It occurs in diverse languages and is prevalent in American English, where it is used not only to mark phrase finality, but also sociolinguistic factors and affect. Due to its irregular periodicity, creaky voice challenges automatic speech processing and recognition systems, particularly for languages where creak is frequently used. This paper proposes a deep learning model to detect creaky voice in fluent speech. The model is composed of an encoder and a classifier trained together. The encoder takes the raw waveform and learns a representation using a convolutional neural network. The classifier is implemented as a multi-headed fully-connected network trained to detect creaky voice, voicing, and pitch, where the last two are used to refine creak prediction. The model is trained and tested on speech of American English speakers, annotated for creak by trained phoneticians. We evaluated the performance of our system using two encoders: one is tailored for the task, and the other is based on a state-of-the-art unsupervised representation. Results suggest our best-performing system has improved recall and F1 scores compared to previous methods on unseen data.

eess.AS↗

arXiv2022

Formant Estimation and Tracking using Probabilistic Heat-Maps

Formants are the spectral maxima that result from acoustic resonances of the human vocal tract, and their accurate estimation is among the most fundamental speech processing problems. Recent work has been shown that those frequencies can accurately be estimated using deep learning techniques. However, when presented with a speech from a different domain than that in which they have been trained on, these methods exhibit a decline in performance, limiting their usage as generic tools. The contribution of this paper is to propose a new network architecture that performs well on a variety of different speaker and speech domains. Our proposed model is composed of a shared encoder that gets as input a spectrogram and outputs a domain-invariant representation. Then, multiple decoders further process this representation, each responsible for predicting a different formant while considering the lower formant predictions. An advantage of our model is that it is based on heatmaps that generate a probability distribution over formant predictions. Results suggest that our proposed model better represents the signal over various domains and leads to better formant frequency tracking and estimation.

cs.SD↗

arXiv2022

THOR: Threshold-Based Ranking Loss for Ordinal Regression

In this work, we present a regression-based ordinal regression algorithm for supervised classification of instances into ordinal categories. In contrast to previous methods, in this work the decision boundaries between categories are predefined, and the algorithm learns to project the input examples onto their appropriate scores according to these predefined boundaries. This is achieved by adding a novel threshold-based pairwise loss function that aims at minimizing the regression error, which in turn minimizes the Mean Absolute Error (MAE) measure. We implemented our proposed architecture-agnostic method using the CNN-framework for feature extraction. Experimental results on five real-world benchmarks demonstrate that the proposed algorithm achieves the best MAE results compared to state-of-the-art ordinal regression algorithms.

cs.LG↗

arXiv2022

Unsupervised Word Segmentation using K Nearest Neighbors

In this paper, we propose an unsupervised kNN-based approach for word segmentation in speech utterances. Our method relies on self-supervised pre-trained speech representations, and compares each audio segment of a given utterance to its K nearest neighbors within the training set. Our main assumption is that a segment containing more than one word would occur less often than a segment containing a single word. Our method does not require phoneme discovery and is able to operate directly on pre-trained audio representations. This is in contrast to current methods that use a two-stage approach; first detecting the phonemes in the utterance and then detecting word-boundaries according to statistics calculated on phoneme patterns. Experiments on two datasets demonstrate improved results over previous single-stage methods and competitive results on state-of-the-art two-stage methods.

cs.SD↗

arXiv2022

Self-supervised Speaker Diarization

Over the last few years, deep learning has grown in popularity for speaker verification, identification, and diarization. Inarguably, a significant part of this success is due to the demonstrated effectiveness of their speaker representations. These, however, are heavily dependent on large amounts of annotated data and can be sensitive to new domains. This study proposes an entirely unsupervised deep-learning model for speaker diarization. Specifically, the study focuses on generating high-quality neural speaker representations without any annotated data, as well as on estimating secondary hyperparameters of the model without annotations. The speaker embeddings are represented by an encoder trained in a self-supervised fashion using pairs of adjacent segments assumed to be of the same speaker. The trained encoder model is then used to self-generate pseudo-labels to subsequently train a similarity score between different segments of the same call using probabilistic linear discriminant analysis (PLDA) and further to learn a clustering stopping threshold. We compared our model to state-of-the-art unsupervised as well as supervised baselines on the CallHome benchmarks. According to empirical results, our approach outperforms unsupervised methods when only two speakers are present in the call, and is only slightly worse than recent supervised models.

cs.SD↗