81 accepted papers
Accurate localization in GPS-denied environments remains a critical challenge for autonomous robot navigation. Animals exhibit remarkable navigational abilities in complex, dynamic environments by relying on mental cognitive maps. Inspired by neural representations such as head direction cells and g…
Emotional information in speech plays a unique role in multimodal perception. However, current Speech Large Language Models (SpeechLLMs), similar to conventional speech emotion recognition (SER) systems, still treat emotion understanding as a simple classification problem. This provides limited inte…
Neural audio codecs are foundational to speech language models. It is expected to have a low frame rate and decoupled semantic and acoustic information. A lower frame rate codec can reduce the computational cost of speech language models by shortening the sequence length. Recent studies have develop…
Recent advances in text-to-speech (TTS) technology have enabled systems to generate speech that is often indistinguishable from human speech, bringing benefits to accessibility, content creation, and human-computer interaction. However, current evaluation practices are increasingly inadequate for ca…
Spatio-temporal epidemic forecasting is critical for public health management, yet existing methods often struggle with insensitivity to weak epidemic signals, over-simplified spatial relations, and unstable parameter estimation. To address these challenges, we propose the Spatio-Temporal priOr-awar
Designing robotic manipulators often requires balancing dexterity, speed, and payload capacity. While traditional serial-link and cable-driven manipulators offer high dexterity, they struggle to concurrently achieve high speed, and often lack the strength and stiffness required for many applications…
Text-to-video (T2V) models have recently undergone rapid and substantial advancements. Nevertheless, due to limitations in data and computational resources, achieving efficient generation of long videos with rich motion dynamics remains a significant challenge. To generate high-quality, dynamic, an…
We present MELLE, a novel continuous-valued token based language modeling approach for text-to-speech synthesis (TTS). MELLE autoregressively generates continuous mel-spectrogram frames directly from text condition, bypassing the need for vector quantization, which is typically designed for audio co…
Large language models (LLMs) have made significant advancements in natural language processing and are concurrently extending the language ability to other modalities, such as speech and vision. Nevertheless, most of the previous work focuses on prompting LLMs with perception abilities like auditory…
Accurate localization in GPS-denied environments remains a critical challenge for autonomous robot navigation. Animals exhibit remarkable navigational abilities in complex, dynamic environments by relying on mental cognitive maps. Inspired by neural representations such as head direction cells and g
Generating natural-sounding, multi-speaker dialogue is crucial for applications such as podcast creation, virtual agents, and multimedia content generation. However, existing systems struggle to maintain speaker consistency, model overlapping speech, and synthesize coherent conversations efficiently…
Generative Error Correction (GEC) has emerged as a powerful post-processing method to boost the performance of Automatic Speech Recognition (ASR) systems. In this paper, we first show that GEC models struggle to generalize beyond the specific types of errors encountered during training, limiting the…
Recent advancements highlight the potential of end-to-end real-time spoken dialogue systems, showcasing their low latency and high quality. In this paper, we introduce SLAM-Omni, a timbre-controllable, end-to-end voice interaction system with single-stage training. SLAM-Omni achieves zero-shot timbr…
End-to-end autonomous driving, which directly maps raw sensor inputs to low-level vehicle controls, is an crucial part of Embodied AI. Despite successes in applying Multimodal Large Language Models (MLLMs) for high-level traffic scene semantic understanding, it remains challenging to effectively tra
Obtaining word timestamp information from end-to-end (E2E) ASR models remains challenging due to the lack of explicit time alignment during training. This issue is further complicated in multilingual models. Existing methods, either rely on lexicons or introduce additional tokens, leading to scalabi…
In this paper, we introduce V2SFlow, a novel Video-to-Speech (V2S) framework designed to generate natural and intelligible speech directly from silent talking face videos. While recent V2S systems have shown promising results on constrained datasets with limited speakers and vocabularies, their perf…
Recent advancements in zero-shot text-to-speech (TTS) modeling have led to significant strides in generating high-fidelity and diverse speech. However, dialogue generation, along with achieving human-like naturalness in speech, continues to be a challenge. In this paper, we introduce CoVoMix: Conver…
End-to-end speech translation (ST) for conversation recordings involves several under-explored challenges such as speaker diarization (SD) without accurate word time stamps and handling of overlapping speech in a streaming fashion. In this work, we propose DiariST, the first streaming ST and SD solu…
The growing need for instant spoken language transcription and translation is driven by increased global communication and cross-lingual interactions. This has made offering translations in multiple languages essential for user applications. Traditional approaches to automatic speech recognition (AS…
While recent large-scale text-to-speech (TTS) models have achieved significant progress, they still fall shorts in speech quality, similarity, and prosody. Considering that speech intricately encompasses various attributes (e.g., content, prosody, timbre, and acoustic details) that pose significant…
Memory constraint of always-on devices is one of the major concerns when deploying speech processing models on these devices. While larger models trained with sufficiently large amount of data generally perform better, making them fit in the device memory is a demanding challenge. In this paper, we…
Token-level serialized output training (t-SOT) was recently proposed to address the challenge of streaming multi-talker automatic speech recognition (ASR). T-SOT effectively handles overlapped speech by representing multi-talker transcriptions as a single token stream with ⟨cc⟩ symbols interspersed.…
There is a rising interest and trend in research towards directly translating speech from one language to another, known as end-to-end speech-to-speech translation. However, most end-to-end models struggle to outperform cascade models, i.e., a pipeline framework by concatenating speech recognition,…
Recent advancements in large language models (LLMs) have expanded their scope in natural language processing (NLP) to encompass multimodal functions. However, integrating listening capabilities effectively remains a significant challenge for generalization and complex auditory task execution. In thi…
In this work, we present a simple but effective method, CTCBERT, for advancing hidden-unit BERT (HuBERT). HuBERT applies a frame-level cross-entropy (CE) loss, which is similar to most acoustic model training. However, CTCBERT performs the model training with the Connectionist Temporal Classificatio…
Neural transducer is now the most popular end-to-end model for speech recognition, due to its naturally streaming ability. However, it is challenging to adapt it with text-only data. Factorized neural transducer (FNT) model was proposed to mitigate this problem. The improved adaptation ability of FN…
We previously proposed contextual spelling correction (CSC) to correct the output of end-to-end (E2E) automatic speech recognition (ASR) models with contextual information such as name, place, etc. Although CSC has achieved reasonable improvement in the biasing problem, there are still two drawbacks…
Direct speech-to-speech translation (S2ST) is an attractive research topic with many advantages compared to cascaded S2ST. However, direct S2ST suffers from the data scarcity problem because the corpora from the speech of the source language to the speech of the target language are very rare. To add…
Traditional automatic speech recognition (ASR) systems usually focus on individual utterances, without considering long-form speech with useful historical information, which is more practical in real scenarios. Simply attending longer transcription history for a vanilla neural transducer model shows…
In order to deal with the sparse and unstructured raw point clouds, most LiDAR based 3D object detection research focuses on designing dedicated local point aggregators for fine-grained geometrical modeling. In this paper, we revisit the local point aggregators from the perspective of allocating com…
Self-supervised learning (SSL), which utilizes the input data itself for representation learning, has achieved state-of-the-art results for various downstream speech tasks. However, most of the previous studies focused on offline single-talker applications, with limited investigations in multi-talke…
Multi-talker automatic speech recognition (ASR) has been studied to generate transcriptions of natural conversation including over-lapping speech of multiple speakers. Due to the difficulty in acquiring real conversation data with high-quality human transcriptions, a naïve simulation of multi-talker…
Speaker change detection (SCD) is an important feature that improves the readability of the recognized words from an automatic speech recognition (ASR) system by breaking the word sequence into paragraphs at speaker change points. Existing SCD solutions either require additional ensemble for the tim…
Self-supervised learning (SSL) methods such as WavLM have shown promising speech separation (SS) results in small-scale simulation-based experiments. In this work, we extend the exploration of the SSL-based SS by massively scaling up both the pre-training data (more than 300K hours) and fine-tuning…
This paper presents a novel streaming automatic speech recognition (ASR) framework for multi-talker overlapping speech captured by a distant microphone array with an arbitrary geometry. Our framework, named t-SOT-VA, capitalizes on independently developed two recent technologies; array-geometry-agno…
Multilingual automatic speech recognition models have shown great promise in recent years because of the simple model training and deployment process. Conventional methods either train a universal multilingual model without taking any language information or with a 1-hot language ID (LID) vector to…
While permutation invariant training (PIT) based continuous speech separation (CSS) significantly improves the conversation transcription accuracy, it often suffers from speech leakages and failures in separation at "hot spot" regions because it has a fixed number of output channels. In this paper,…
Streaming recognition of multi-talker conversations has so far been evaluated only for 2-speaker single-turn sessions. In this paper, we investigate it for multi-turn meetings containing multiple speakers using the Streaming Unmixing and Recognition Transducer (SURT) model, and show that naively ext…
Streaming end-to-end multi-talker speech recognition aims at transcribing the overlapped speech from conversations or meetings with an all-neural model in a streaming fashion, which is fundamentally different from a modular-based approach that usually cascades the speech separation and the speech re…
In recent years, end-to-end (E2E) based automatic speech recognition (ASR) systems have achieved great success due to their simplicity and promising performance. Neural Transducer based models are increasingly popular in streaming E2E based ASR systems and have been reported to outperform the tradit…
Hybrid and end-to-end (E2E) systems have their individual advantages, with different error patterns in the speech recognition results. By jointly modeling audio and text, the E2E model performs better in matched scenarios and scales well with a large amount of paired audio-text training data. The mo…
Noise robustness is essential for deploying automatic speech recognition (ASR) systems in real-world environments. One way to reduce the effect of noise interference is to employ a preprocessing module that conducts speech enhancement, and then feed the enhanced speech to an ASR backend. In this wor…
Recently, pioneer work finds that self-supervised pre-training methods can improve multiple downstream speech tasks, because the model utilizes bottom layers to learn speaker-related information and top layers to encode content-related information. Since the network capacity is limited, we believe t…
Motivated by the success of T5 (Text-To-Text Transfer Transformer) in pre-trained natural language processing models, we propose a unified-modal SpeechT5 framework that explores the encoder-decoder pre-training for self-supervised speech/text representation learning. The SpeechT5 framework consists…
The rapid development of single-modal pre-training has prompted researchers to pay more attention to cross-modal pre-training methods. In this paper, we propose a unified-modal speech-unit-text pre-training model, SpeechUT, to connect the representations of a speech encoder and a text decoder with a…
Self-supervised learning (SSL) is a long-standing goal for speech processing, since it utilizes large-scale unlabeled data and avoids extensive human labeling. Recent years have witnessed great successes in applying self-supervised learning in speech recognition, while limited exploration was attemp…
The goal of self-supervised learning (SSL) for automatic speech recognition (ASR) is to learn good speech representations from a large amount of unlabeled speech for the downstream ASR task. However, most SSL frameworks do not consider noise robustness which is crucial for real-world applications. I…
Continuous speech separation was recently proposed to deal with the overlapped speech in natural conversations. While it was shown to significantly improve the speech recognition performance for multichannel conversation transcription, its effectiveness has yet to be proven for a single-channel reco…
Recently, Transformer based end-to-end models have achieved great success in many areas including speech recognition. However, compared to LSTM models, the heavy computational cost of the Transformer during inference is a key issue to prevent their applications. In this work, we explored the potenti…
Hypothesis-level combination between multiple models can often yield gains in speech recognition. However, all models in the ensemble are usually restricted to use the same audio segmentation times. This paper proposes to generalise hypothesis-level combination, allowing the use of different audio s…
The efficacy of external language model (LM) integration with existing end-to-end (E2E) automatic speech recognition (ASR) systems can be improved significantly using the internal language model estimation (ILME) method [1]. In this method, the internal LM score is subtracted from the score obtained…
This paper describes the Microsoft speaker diarization system for monaural multi-talker recordings in the wild, evaluated at the diarization track of the VoxCeleb Speaker Recognition Challenge (VoxSRC) 2020. We will first explain our system design to address issues in handling real multi-talker reco…
This paper describes a dataset and protocols for evaluating continuous speech separation algorithms. Most prior speech separation studies use pre-segmented audio signals, which are typically generated by mixing speech utterances on computers so that they fully overlap. Also, the separation algorithm…
Recently, the recurrent neural network transducer (RNN-T) architecture has become an emerging trend in end-to-end automatic speech recognition research due to its advantages of being capable for online streaming speech recognition. However, RNN-T training is made difficult by the huge memory require…
While the community keeps promoting end-to-end models over conventional hybrid models, which usually are long short-term memory (LSTM) models trained with a cross entropy criterion followed by a sequence discriminative training criterion, we argue that such conventional hybrid models can still be si…
We propose a novel neural label embedding (NLE) scheme for the domain adaptation of a deep neural network (DNN) acoustic model with unpaired data samples from source and target domains. With NLE method, we distill the knowledge from a powerful source-domain DNN into a dictionary of label embeddings,…
Recently, a few novel streaming attention-based sequence-to-sequence (S2S) models have been proposed to perform online speech recognition with linear-time decoding complexity. However, in these models, the decisions to generate tokens are delayed compared to the actual acoustic boundaries since thei…
We propose to use the personalized speech synthesis and the neural language generator to synthesize content relevant personalized speech for rapid speaker adaptation. It has two distinct aspects: First, it relieves the general data sparsity issue in rapid adaptation via making use of additional synt…
We propose a novel adversarial speaker adaptation (ASA) scheme, in which adversarial learning is applied to regularize the distribution of deep hidden features in a speaker-dependent (SD) deep neural network (DNN) acoustic model to be close to that of a fixed speaker-independent (SI) DNN acoustic mo…
The use of deep networks to extract embeddings for speaker recognition has proven successfully. However, such embeddings are susceptible to performance degradation due to the mismatches among the training, enrollment, and test conditions. In this work, we propose an adversarial speaker verification…
Adversarial domain-invariant training (ADIT) proves to be effective in suppressing the effects of domain variability in acoustic modeling and has led to improved performance in automatic speech recognition (ASR). In ADIT, an auxiliary domain classifier takes in equally-weighted deep features from a…
The teacher-student (T/S) learning has been shown to be effective for a variety of problems such as domain adaptation and model compression. One shortcoming of the T/S learning is that a teacher model, not always perfect, sporadically produces wrong guidance in form of posterior probabilities that m…
In our recent work, we proposed a layer trajectory long short-term memory (ltLSTM) model which decouples the tasks of temporal modeling and senone classification with time-LSTMs and depth-LSTMs. The ltLSTM model achieved significant accuracy improvement over the traditional multi-layer LSTM models f…
Monocular visual-inertial tracking without good initialization easily fails due to its non-linear nature. Rapid and accurate metric initialization is crucial. In this paper, we propose a novel monocular visual-inertial initialization method which can initialize the IMU states, camera poses, and scal…
Although great progress has been made on end-to-end (E2E) models for monolingual and multilingual automatic speech recognition (ASR), there is no successful study for E2E models on the challenging intra-sentential code-switching (CS) ASR task to our best knowledge. In this paper, we propose an appro…
Acoustic models are domain dependent and do not perform well if there is a mismatch between training and test conditions. As an alternative, the Mixture of Experts (MoE) model was introduced for multi-domain modeling. It combines the outputs of several domain specific models (or experts) using a gat…
The acoustic-to-word model based on the connectionist temporal classification (CTC) criterion was shown as a natural end-to-end (E2E) model directly targeting words as output units. However, the word-based CTC model suffers from the out-of-vocabulary (OOV) issue as it can only model limited number o…
In this study, we propose advancing all-neural speech recognition by directly incorporating attention modeling within the Connectionist Temporal Classification (CTC) framework. In particular, we derive new context vectors using time convolution features to model attention as part of the CTC network.…
The teacher-student (T/S) learning has been shown effective in unsupervised domain adaptation [1]. It is a form of transfer learning, not in terms of the transfer of recognition decisions, but the knowledge of posteriori probabilities in the source domain as evaluated by the teacher model. It learns…
In this study, we develop the keyword spotting (KWS) and acoustic model (AM) components in a far-field speaker system. Specifically, we use teacher-student (T/S) learning to adapt a close-talk well-trained production AM to far-field by using parallel close-talk and simulated far-field data. We also…
Voice assistant represents one of the most popular and important scenarios for speech recognition. In this paper, we propose two adaptation approaches to customize a multi-style well-trained acoustic model towards its subsidiary domain of Cortana assistant. First, we present anchor-based speaker ada…
We propose a novel adversarial multi-task learning scheme, aiming at actively curtailing the inter-talker feature variability while maximizing its senone discriminability so as to enhance the performance of a deep neural network (DNN) based ASR system. We call the scheme speaker-invariant training (…
Recently, the low-rank plus diagonal (LRPD) adaptation was proposed for speaker adaptation of deep neural network (DNN) models. The LRPD restructures the adaptation matrix as a superposition of a diagonal matrix and a product of two low-rank matrices. In this paper, we extend the LRPD adaptation int…
In the era of deep learning, although beam-forming multi-channel signal processing is still very helpful, it was reported that single-channel robust front-ends usually cannot benefit deep learning models because the layer-by-layer structure of deep learning models provides a feature extraction strat…
Long short-term memory (LSTM) recurrent neural networks (RNNs) have recently shown significant performance improvements over deep feed-forward neural networks. A key aspect of these models is the use of time recurrence, combined with a gating architecture that allows them to track the long-term dyna…
In this paper, we propose a scalable adaptation technique that adapts the deep neural network (DNN) model through the low-rank plus diagonal (LRPD) decomposition. It is desired that an adaptation method can properly accommodate the available development data with a variable amount of adaptation para…
Recurrent Neural Networks (RNNs) using Long-Short Term Memory (LSTM) architecture have demonstrated the state-of-the-art performances on speech recognition. Most of deep RNNs use the softmax activation function in the last layer for classification. This paper illustrates small but consistent advanta…
On acoustic modeling, recurrent neural networks (RNNs) using Long Short-Term Memory (LSTM) units have recently been shown to outperform deep neural networks (DNNs) models. This paper focuses on resolving two challenges faced by LSTM models: high model complexity and poor decoding efficiency. Motivat…
Despite the fact that several sites have reported the effectiveness of convolutional neural networks (CNNs) on some tasks, there is no deep analysis regarding why CNNs perform well and in which case we should see CNNs' advantage. In the light of this, this paper aims to provide some detailed analysi…
To develop speaker adaptation algorithms for deep neural network (DNN) that are suitable for large-scale online deployment, it is desirable that the adaptation model be represented in a compact form and learned in an unsupervised fashion. In this paper, we propose a novel low-footprint adaptation te…
Due to a large number of parameters in deep neural networks (DNNs), it is challenging to design a small-footprint DNN-based speech recognition system while maintaining a high recognition performance. Even with a singular value matrix decomposition (SVD) method and scalar quantization, the DNN model…