相关论文: Efficient Keyword Spotting by capturing long-range…

With the advent of conversational assistants, like Amazon Alexa, Google Now, etc., dialogue systems are gaining a lot of traction, especially in industrial setting. These systems typically consist of Spoken Language understanding component…

Transformers have seen an unprecedented rise in Natural Language Processing and Computer Vision tasks. However, in audio tasks, they are either infeasible to train due to extremely large sequence length of audio waveforms or incur a…

Transformers, known for their attention mechanisms, have proven highly effective in focusing on critical elements within complex data. This feature can effectively be used to address the time-varying channels in wireless communication…

Robustness against noise is critical for keyword spotting (KWS) in real-world environments. To improve the robustness, a speech enhancement front-end is involved. Instead of treating the speech enhancement as a separated preprocessing…

In this work, we propose Retentive Network (RetNet) as a foundation architecture for large language models, simultaneously achieving training parallelism, low-cost inference, and good performance. We theoretically derive the connection…

Sentence matching is widely used in various natural language tasks such as natural language inference, paraphrase identification, and question answering. For these tasks, understanding logical and semantic relationship between two sentences…

Keyword Spotting (KWS) enables speech-based user interaction on smart devices. Always-on and battery-powered application scenarios for smart devices put constraints on hardware resources and power consumption, while also demanding high…

We propose a direct-to-word sequence model which uses a word network to learn word embeddings from letters. The word network can be integrated seamlessly with arbitrary sequence models including Connectionist Temporal Classification and…

We present a novel non attention based architecture for large language models (LLMs) that efficiently handles very long context windows, on the order of hundreds of thousands to potentially millions of tokens. Unlike traditional Transformer…

Most current speech enhancement models use spectrogram features that require an expensive transformation and result in phase information loss. Previous work has overcome these issues by using convolutional networks to learn long-range…

Spatial-wise dynamic convolution has become a promising approach to improving the inference efficiency of deep networks. By allocating more computation to the most informative pixels, such an adaptive inference paradigm reduces the spatial…

Most state-of-the-art Deep Learning (DL) approaches for speaker recognition work on a short utterance level. Given the speech signal, these algorithms extract a sequence of speaker embeddings from short segments and those are averaged to…

Active learning of timed languages is concerned with the inference of timed automata from observed timed words. The agent can query for the membership of words in the target language, or propose a candidate model and verify its equivalence…

Late-interaction retrieval models like ColBERT achieve superior accuracy by enabling token-level interactions, but their computational cost hinders scalability and integration with Approximate Nearest Neighbor Search (ANNS). We introduce…

While automatic response generation for building chatbot systems has drawn a lot of attention recently, there is limited understanding on when we need to consider the linguistic context of an input text in the generation process. The task…

Building efficient architecture in neural speech processing is paramount to success in keyword spotting deployment. However, it is very challenging for lightweight models to achieve noise robustness with concise neural operations. In a…

Classifying semantic relations between entity pairs in sentences is an important task in Natural Language Processing (NLP). Most previous models for relation classification rely on the high-level lexical and syntactic features obtained by…

Network embedding has recently emerged as a promising technique to embed nodes of a network into low-dimensional vectors. While fairly successful, most existing works focus on the embedding techniques for static networks. But in practice,…

Transformer-based language models have recently been at the forefront of active research in text generation. However, these models' advances come at the price of prohibitive training costs, with parameter counts in the billions and compute…

High-dimensional, heterogeneous data with complex feature interactions pose significant challenges for traditional predictive modeling approaches. While Projection to Latent Structures (PLS) remains a popular technique, it struggles to…