English
Related papers

Related papers: Serialized Output Training by Learned Dominance

200 papers

Task-oriented Dialog (ToD) systems have to solve multiple subgoals to accomplish user goals, whereas feedback is often obtained only at the end of the dialog. In this work, we propose SUIT (SUbgoal-aware ITerative Training), an iterative…

Computation and Language · Computer Science 2024-11-26 Magdalena Kaiser , Patrick Ernst , György Szarvas

Sequence labelling tasks like Dialog Act and Emotion/Sentiment identification are a key component of spoken dialog systems. In this work, we propose a new approach to learn generic representations adapted to spoken dialog, which we evaluate…

Computation and Language · Computer Science 2021-02-09 Emile Chapuis , Pierre Colombo , Matteo Manica , Matthieu Labeau , Chloe Clavel

We propose a novel deep learning model, which supports permutation invariant training (PIT), for speaker independent multi-talker speech separation, commonly known as the cocktail-party problem. Different from most of the prior arts that…

Computation and Language · Computer Science 2018-12-06 Dong Yu , Morten Kolbæk , Zheng-Hua Tan , Jesper Jensen

The complex world around us is inherently multimodal and sequential (continuous). Information is scattered across different modalities and requires multiple continuous sensors to be captured. As machine learning leaps towards better…

Machine Learning · Computer Science 2019-11-25 Amir Zadeh , Chengfeng Mao , Kelly Shi , Yiwei Zhang , Paul Pu Liang , Soujanya Poria , Louis-Philippe Morency

We present a real-time front-end for voice-based conversational AI to enable natural turn-taking in two-speaker scenarios by combining primary speaker segmentation with hierarchical End-of-Turn (EOT) detection. To operate robustly in…

Machine Learning · Computer Science 2026-03-17 Karim Helwani , Hoang Do , James Luan , Sriram Srinivasan

An embedding-based speaker adaptive training (SAT) approach is proposed and investigated in this paper for deep neural network acoustic modeling. In this approach, speaker embedding vectors, which are a constant given a particular speaker,…

Computation and Language · Computer Science 2017-10-20 Xiaodong Cui , Vaibhava Goel , George Saon

Traditional transfer learning typically reuses large pre-trained networks by freezing some of their weights and adding task-specific layers. While this approach is computationally efficient, it limits the model's ability to adapt to…

Computer Vision and Pattern Recognition · Computer Science 2025-10-13 Nicolas Ewen , Jairo Diaz-Rodriguez , Kelly Ramsay

In this paper, we present a novel training method for speaker change detection models. Speaker change detection is often viewed as a binary sequence labelling problem. The main challenges with this approach are the vagueness of annotated…

Audio and Speech Processing · Electrical Eng. & Systems 2022-05-17 Joonas Kalda , Tanel Alumäe

Recent research shows end-to-end ASR systems can recognize overlapped speech from multiple speakers. However, all published works have assumed no latency constraints during inference, which does not hold for most voice assistant…

Audio and Speech Processing · Electrical Eng. & Systems 2021-02-22 Ilya Sklyar , Anna Piunova , Yulan Liu

Recent works in dialogue state tracking (DST) focus on an open vocabulary-based setting to resolve scalability and generalization issues of the predefined ontology-based approaches. However, they are inefficient in that they predict the…

Computation and Language · Computer Science 2020-05-05 Sungdong Kim , Sohee Yang , Gyuwan Kim , Sang-Woo Lee

Automatic Speech Understanding (ASU) leverages the power of deep learning models for accurate interpretation of human speech, leading to a wide range of speech applications that enrich the human experience. However, training a robust ASU…

Sound · Computer Science 2023-06-14 Tiantian Feng , Digbalay Bose , Xuan Shi , Shrikanth Narayanan

DeepFake face swapping enables highly realistic identity forgeries, posing serious privacy and security risks. A common defence embeds invisible perturbations into images, but these are fragile and often destroyed by basic transformations…

Computer Vision and Pattern Recognition · Computer Science 2025-12-09 Hengyang Yao , Lin Li , Ke Sun , Jianing Qiu , Huiping Chen

The primary goal of multi-modal TSE (MTSE) is to extract a target speaker from a speech mixture using complementary information from different modalities, such as audio enrolment and visual feeds corresponding to the target speaker. MTSE…

Audio and Speech Processing · Electrical Eng. & Systems 2025-07-10 Srikanth Korse , Mohamed Elminshawi , Emanuel A. P. Habets , Srikanth Raj Chetupalli

Speaker-attributed automatic speech recognition (SA-ASR) in multi-party meeting scenarios is one of the most valuable and challenging ASR task. It was shown that single-channel frame-level diarization with serialized output training…

Audio and Speech Processing · Electrical Eng. & Systems 2023-03-03 Mohan Shi , Jie Zhang , Zhihao Du , Fan Yu , Qian Chen , Shiliang Zhang , Li-Rong Dai

The Streaming Unmixing and Recognition Transducer (SURT) has recently become a popular framework for continuous, streaming, multi-talker speech recognition (ASR). With advances in architecture, objectives, and mixture simulation methods, it…

Audio and Speech Processing · Electrical Eng. & Systems 2024-01-30 Desh Raj , Matthew Wiesner , Matthew Maciejewski , Leibny Paola Garcia-Perera , Daniel Povey , Sanjeev Khudanpur

In schema-guided dialogue state tracking models estimate the current state of a conversation using natural language descriptions of the service schema for generalization to unseen services. Prior generative approaches which decode slot…

Computation and Language · Computer Science 2023-06-16 Björn Bebensee , Haejun Lee

Information on speaker characteristics can be useful as side information in improving speaker recognition accuracy. However, such information is often private. This paper investigates how privacy-preserving learning can improve a speaker…

Audio and Speech Processing · Electrical Eng. & Systems 2020-08-07 Filip Granqvist , Matt Seigel , Rogier van Dalen , Áine Cahill , Stephen Shum , Matthias Paulik

Large Language Models are increasingly being deployed to extract structured data from unstructured and semi-structured sources: parsing invoices, medical records, and converting PDF documents to database entries. Yet existing benchmarks for…

Computation and Language · Computer Science 2026-04-29 Abhinav Kumar Singh , Harsha Vardhan Khurdula , Yoeven D Khemlani , Vineet Agarwal

Conventional spoken language understanding systems consist of two main components: an automatic speech recognition module that converts audio to a transcript, and a natural language understanding module that transforms the resulting text…

Audio and Speech Processing · Electrical Eng. & Systems 2021-02-16 Parisa Haghani , Arun Narayanan , Michiel Bacchiani , Galen Chuang , Neeraj Gaur , Pedro Moreno , Rohit Prabhavalkar , Zhongdi Qu , Austin Waters

Unsupervised action segmentation has recently pushed its limits with ASOT, an optimal transport (OT)-based method that simultaneously learns action representations and performs clustering using pseudo-labels. Unlike other OT-based…

Computer Vision and Pattern Recognition · Computer Science 2025-08-08 Elena Bueno-Benito , Mariella Dimiccoli