相关论文: Towards Listening to 10 People Simultaneously: An …

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…

Serialized Output Training (SOT) has showcased state-of-the-art performance in multi-talker speech recognition by sequentially decoding the speech of individual speakers. To address the challenging label-permutation issue, prior methods…

Weight tying is widely used in compact language models to reduce parameters by sharing the token table between the input embedding and the output projection. However, parameter sharing alone does not guarantee a stable token interface:…

Distributed training of large neural networks is bottlenecked by full-precision gradient communication and by coordinatewise optimizers that ignore the matrix structure of weight tensors. We propose Sign-Muon, a 1-bit, matrix-aware…

Spoofing detection systems are typically trained using diverse recordings from multiple speakers, often assuming that the resulting embeddings are independent of speaker identity. However, this assumption remains unverified. In this paper,…

Deep learning techniques for separating audio into different sound sources face several challenges. Standard architectures require training separate models for different types of audio sources. Although some universal separators employ a…

We consider the problem of single-channel audio source separation with the goal of reconstructing $K$ sources from their mixture. We address this ill-posed problem with FLOSS (FLOw matching for Source Separation), a constrained generation…

Music source separation is important for applications such as karaoke and remixing. Much of previous research focuses on estimating short-time Fourier transform (STFT) magnitude and discarding phase information. We observe that, for singing…

Neural Machine Translation (NMT) approaches employing monolingual data are showing steady improvements in resource rich conditions. However, evaluations using real-world low-resource languages still result in unsatisfactory performance.…

In this thesis, we propose an artificial auditory system that gives a robot the ability to locate and track sounds, as well as to separate simultaneous sound sources and recognising simultaneous speech. We demonstrate that it is possible to…

Post-training quantization has emerged as the most widely used strategy for deploying large language models at low precision. Still, current methods show perplexity degradation at bit-widths less than or equal to 4, partly because…

Sentence Split and Rephrase aims to break down a complex sentence into several simple sentences with its meaning preserved. Previous studies tend to address the issue by seq2seq learning from parallel sentence pairs, which takes a complex…

Sorting and permutation learning are key concepts in optimization and machine learning, especially when organizing high-dimensional data into meaningful spatial layouts. The Gumbel-Sinkhorn method, while effective, requires N*N parameters…

Self-supervised speech representation models have succeeded in various tasks, but improving them for content-related problems using unlabeled data is challenging. We propose speaker-invariant clustering (Spin), a novel self-supervised…

In this paper, we propose the coarse-to-fine optimization for the task of speech enhancement. Cosine similarity loss [1] has proven to be an effective metric to measure similarity of speech signals. However, due to the large variance of the…

We introduce Wavesplit, an end-to-end source separation system. From a single mixture, the model infers a representation for each source and then estimates each source signal given the inferred representations. The model is trained to…

We create a reusable Transformer, BrainBERT, for intracranial recordings bringing modern representation learning approaches to neuroscience. Much like in NLP and speech recognition, this Transformer enables classifying complex concepts,…

We propose an independence-based joint dereverberation and separation method with a neural source model. We introduce a neural network in the framework of time-decorrelation iterative source steering, which is an extension of independent…

We introduce Data Diversification: a simple but effective strategy to boost neural machine translation (NMT) performance. It diversifies the training data by using the predictions of multiple forward and backward models and then merging…

Cross-modal matching, a fundamental task in bridging vision and language, has recently garnered substantial research interest. Despite the development of numerous methods aimed at quantifying the semantic relatedness between image-text…