Sequence to Multi-Sequence Learning via Conditional Chain Mapping for Mixture Signals
Neural sequence-to-sequence models are well established for applications which can be cast as mapping a single input sequence into a single output sequence. In this work, we focus on one-to-many sequence transduction problems, such as extracting multiple sequential sources from a mixture sequence. We extend the standard sequence-to-sequence model to a conditional multi-sequence model, which explicitly models the relevance between multiple output sequences with the probabilistic chain rule. Based on this extension, our model can conditionally infer output sequences one-by-one by making use of both input and previously-estimated contextual output sequences. This model additionally has a simple and efficient stop criterion for the end of the transduction, making it able to infer the variable number of output sequences. We take speech data as a primary test field to evaluate our methods since the observed speech data is often composed of multiple sources due to the nature of the superposition principle of sound waves. Experiments on several different tasks including speech separation and multi-speaker speech recognition show that our conditional multi-sequence models lead to consistent improvements over the conventional non-conditional models.
Code (0)
등록된 구현이 없습니다.
Tasks
speech-recognitionSpeech RecognitionSpeech SeparationSimilar Papers 제목 키워드 기반
Mixing Properties of Conditional Markov Chains with Unbounded Feature Functions
Conditional Markov Chains (also known as Linear-Chain Conditional Random Fields in the literature) are a versatile class of discriminative models for the distribution of a sequence of hidden states conditional on a sequ…
Multi-Speaker ASR Combining Non-Autoregressive Conformer CTC and Conditional Speaker Chain
Non-autoregressive (NAR) models have achieved a large inference computation reduction and comparable results with autoregressive (AR) models on various sequence to sequence tasks. However, there has been limited research…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech RecognitionSequence Classification with Neural Conditional Random Fields
The proliferation of sensor devices monitoring human activity generates voluminous amount of temporal sequences needing to be interpreted and categorized. Moreover, complex behavior detection requires the personalization…
ClassificationGeneral ClassificationPart-Of-Speech TaggingPrediction+4Modiff: Action-Conditioned 3D Motion Generation with Denoising Diffusion Probabilistic Models
Diffusion-based generative models have recently emerged as powerful solutions for high-quality synthesis in multiple domains. Leveraging the bidirectional Markov chains, diffusion probabilistic models generate samples by…
DenoisingMotion GenerationMixing Times of Glauber Dynamics on Masked Language Models
Masked language models (MLMs) define local conditional distributions over tokens but do not, in general, correspond to any consistent joint distribution over sequences. This raises a fundamental question: what global dis…