47 accepted papers
Simulation-based training offers an efficient paradigm for robotic skill learning, providing scalable data generation while reducing reliance on costly hardware trials and manual data collection. However, existing methods that rely on handcrafted scenarios fail to fully cover the complexity of open-…
Transparent objects remain notoriously hard for perception systems: refraction, reflection and transmission break the assumptions behind stereo, ToF and purely discriminative monocular depth, causing holes and temporally unstable estimates. Our key observation is that modern video diffusion models a…
Recommender systems (RS) are widely used in e-commerce for personalized suggestions, yet their openness makes them susceptible to shilling attacks, where adversaries inject fake behaviors to manipulate recommendations. Most existing defenses emphasize user-side behaviors while overlooking item-side…
Recently, the application of diffusion probabilistic models has advanced speech enhancement through generative approaches. However, existing diffusion-based methods have focused on the generation process in high-dimensional waveform or spectral domains, leading to increased generation complexity and…
The application of generative adversarial networks (GANs) has recently advanced speech super-resolution (SR) based on intermediate representations like mel-spectrograms. However, existing SR methods that typically rely on independently trained and concatenated networks may lead to inconsistent repre…
Achieving high-fidelity audio compression while preserving perceptual quality across diverse audio types remains a significant challenge in Neural Audio Coding (NAC). This paper introduces MUFFIN, a fully convolutional NAC framework that leverages psychoacoustically guided multi-band frequency recon…
Adversarial examples have been shown to deceive Deep Neural Networks (DNNs), raising widespread concerns about this security threat. More seriously, as different DNN models share critical features, feature-level attacks can generate transferable adversarial examples, thereby deceiving black-box mode…
Non-intrusive speech quality assessment (NISQA) is widely used in speech downstream tasks due to its ability to predict the quality of speech without a reference speech. However, few researchers have focused on the backdoor security of NISQA. Despite the backdoor defenses have been extensively studi…
Backdoor attacks pose a significant threat during the model's training phase. Attackers craft pre-defined triggers to break deep neural networks, ensuring the model accurately classifies clean samples during inference yet erroneously classifies samples added with these triggers. Recent studies have…
Large self-supervised pre-trained speech models require computationally expensive fine-tuning for downstream tasks. Soft prompt tuning offers a simple parameter-efficient alternative by utilizing minimal soft prompt guidance, enhancing portability while also maintaining competitive performance. Howe…
Our previously proposed MossFormer has achieved promising performance in monaural speech separation. However, it predominantly adopts a self-attention-based MossFormer module, which tends to emphasize longer-range, coarser-scale dependencies, with a deficiency in effectively modelling finer-scale re…
Dual-path is a popular architecture for speech separation models (e.g. Sepformer) which splits long sequences into overlapping chunks for its intra- and inter-blocks that separately model intra-chunk local features and inter-chunk global relationships. However, it has been found that inter-blocks, w…
Learning on a massive amount of speech corpus leads to the recent success of many self-supervised speech models. With knowledge distillation, these models may also benefit from the knowledge encoded by language models that are pre-trained on rich sources of texts. The distillation process, however,…
End-to-end spoken language understanding requires speech data annotated with semantic information and may suffer from the shortage of annotated data. Recent progresses leverage unlabelled speech data to pre-train a speech encoder. However, it remains a challenge for the pre-trained speech encoder to…
Most of the existing neural-based models for keyword spotting (KWS) in smart devices require thousands of training samples to learn a decent audio representation. However, with the rising demand for smart devices to become more person-alized, KWS models need to adapt quickly to smaller user samples.…
Monaural speech enhancement has been widely studied using real networks in the time-frequency (TF) domain. However, the input and the target are naturally complex-valued in the TF domain, a fully complex network is highly desirable for effectively learning the feature representation and modelling th…
Existing self-supervised pre-trained speech models have offered an effective way to leverage massive unannotated corpora to build good automatic speech recognition (ASR). However, many current models are trained on a clean corpus from a single source, which tends to do poorly when noise is present d…
Transformer based models have provided significant performance improvements in monaural speech separation. However, there is still a performance gap compared to a recent proposed upper bound. The major limitation of the current dual-path Transformer models is the inefficient modelling of long-range…
Speech translation models benefit from adapting multilingual pretrained language models. However, such adaptation modifies the parameters in the pretrained model to favor a specific task. Prefix-tuning, as a lightweight adaptation technique, has recently emerged as an efficient adaptation method tha…
Echo and noise suppression is an integral part of a full-duplex communication system. Many recent acoustic echo cancellation (AEC) systems rely on a separate adaptive filtering module for linear echo suppression and a neural module for residual echo suppression. However, in practice, adaptive filter…
Convolutional recurrent networks (CRN) integrating a convolutional encoder-decoder (CED) structure and a recurrent structure have achieved promising performance for monaural speech enhancement. However, feature representation across frequency context is highly constrained due to limited receptive fi…
Recent development of speech signal processing, such as speech recognition, speaker diarization, etc., has inspired numerous applications of speech technologies. The meeting scenario is one of the most valuable and, at the same time, most challenging scenarios for the deployment of speech technologi…
Multimodal sentiment analysis is built on fusion of inputs from multiple modalities. However, at the core of existing fusion method is the dot product between a key vector and a query vector and relies on multiple neural network layers to model the high-order correlation. In this paper, we present a…
The ICASSP 2022 Multi-channel Multi-party Meeting Transcription Grand Challenge (M2MeT) focuses on one of the most valuable and the most challenging scenarios of speech technologies. The M2MeT challenge has particularly set up two tracks, speaker diarization (track 1) and multi-speaker automatic spe…
Transformer models have been used in automatic speech recognition (ASR) successfully and yields state-of-the-art results. However, its performance is still affected by speaker mismatch between training and test data. Further finetuning a trained model with target speaker data is the most natural app…
Deep complex U-Net structure and convolutional recurrent network (CRN) structure achieve state-of-the-art performance for monaural speech enhancement. Both deep complex U-Net and CRN are encoder and decoder structures with skip connections, which heavily rely on the representation power of the compl…
With the recent development of end-to-end models in speech recognition, there have been more interests in adapting these models for online speech recognition. However, using end-to-end models for online speech recognition is known to suffer from an early endpointing problem, which brings in many del…
Cross-lingual voice conversion (VC) is an important and challenging problem due to significant mismatches of the phonetic set and the speech prosody of different languages. In this paper, we build upon the neural text-to-speech (TTS) model, i.e., FastSpeech, and LPCNet neural vocoder to design a new…
The attention-based end-to-end (E2E) automatic speech recognition (ASR) architecture allows for joint optimization of acoustic and language models within a single network. However, in a vanilla E2E ASR architecture, the decoder sub-network (subnet), which incorporates the role of the language model…
Audio-visual speech recognition (AVSR) is thought to be one of the potential solutions for robust speech recognition, especially in noisy environments. Compared to audio only speech recognition, the major issues of AVSR include the lack of publicly available audio-visual corpora and the need of robu…
This paper proposes a new medical image super-resolution (SR) network, namely deep multi-scale network (DMSN), in the uniform discrete curvelet transform (UDCT) domain. DMSN is made up of a set of cascaded multi-scale fushion (MSF) blocks. In each MSF block, we use convolution kernels of different s…
Probabilistic linear discriminant analysis (PLDA) is widely described as an effective model for text-independent speaker verification in the i-vector space. The PLDA scoring function is typically formulated as the likelihood ratio between the speaker-adapted and the universal PLDAs. In this case, th…
Training a bottleneck feature (BNF) extractor with multilingual data has been common in low resource keyword search. In a low resource application, the amount of transcribed target language data is limited while there are usually plenty of multilingual data. In this paper, we investigated two method…
Speech recognition performance deteriorates in face of unknown noise. Speech enhancement offers a solution by reducing the noise in speech at runtime. However, it also introduces artificial distortions to the speech signals. In this paper, we aim at reducing the artifacts that has adverse effects on…
We propose to use a feature representation obtained by pairwise learning in a low-resource language for query-by-example spoken term detection (QbE-STD). We assume that word pairs identified by humans are available in the low-resource target language. The word pairs are parameterized by a multi-ling…
Dynamic Time Warping (DTW) is widely used in language independent query-by-example (QbE) spoken term detection (STD) tasks due to its high performance. However, there are two limitations of DTW based template matching, 1) it is not straightforward to perform approximate match of audio queries; 2) DT…
I-vector has shown to be very effective in speaker verification with long-duration speech utterances. But when test utterances are of short duration, content mismatch between the enrollment and test utterances limit the performance of i-vector system. This paper proposes to extract local session var…
In this paper, we propose a cross-lingual deep neural network (DNN) based submodular unbiased data selection approach for low-resource keyword search (KWS). A small amount (e.g. one hour) of transcribed data is used to conduct cross-lingual transfer. The frame-level senone sequence activated by the…
A recent trend in normalization of factors extraneous to a speech recognition task has been to explicitly introduce features related to the unwanted variability in the training of Deep Neural Networks (DNN). Typically, this is done by either perturbing the training set with models of these extraneou…
We present exemplar-inspired low-resource spoken keyword search strategies for acoustic modeling, keyword verification, and system combination. This state-of-the-art system was developed by the SINGA team in the context of the 2015 NIST Open Keyword Search Evaluation (OpenKWS15) using conversational…
This paper presents a new approach and the study of GMM-SVM system for text-dependent speaker recognition on scenario of the fixed pass-phrases. The uniform-split content-based GMM-SVM system is proposed and applied to text-dependent speaker evaluation. We conducted detailed study of the proposed me…
Probabilistic linear discriminant analysis (PLDA) has shown to be effective for modeling channel variability in the i-vector space for text-independent speaker verification. Speaker verification is a binary hypothesis testing. Given a test segment, the verification score could be computed as the log…
In this paper, we propose a partial sequence matching based symbolic search (SS) method for the task of language independent query-by-example spoken term detection. One main drawback of conventional SS approach is the high miss rate for long queries. This is due to high variations in symbol represen…
We propose strategies for a state-of-the-art keyword search (KWS) system developed by the SINGA team in the context of the 2014 NIST Open Keyword Search Evaluation (OpenKWS14) using conversational Tamil provided by the IARPA Babel program. To tackle low-resource challenges and the rich morphological…
In this paper, we propose to use acoustic feature based submodular function optimization to select a subset of untranscribed data for manual transcription, and retrain the initial acoustic model with the additional transcribed data. The acoustic features are obtained from an unsupervised Gaussian mi…
Tone error is commonly observed in tonal language acquisition. Correct tone production is especially challenging for native speakers of non-tonal languages. In this paper, we exploit the fundamental frequency variation (FFV) feature for Mandarin tone error detection. We propose to use FFV through tw…
This paper considers an unsupervised data selection problem for the training data of an acoustic model and the vocabulary coverage of a keyword search system in low-resource settings. We propose to use Gaussian component index based n-grams as acoustic features in a submodular function for unsupervi…