2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)最新文献_第4页

Computational cost reduction of long short-term memory based on simultaneous compression of input and hidden state 基于输入和隐藏状态同步压缩的长短期记忆计算成本降低

2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) Pub Date : 2017-12-01 DOI: 10.1109/ASRU.2017.8268926

T. Masuko

引用次数: 8

The USTC system for blizzard machine learning challenge 2017-ES2 暴雪机器学习挑战赛2017-ES2的USTC系统

2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) Pub Date : 2017-12-01 DOI: 10.1109/ASRU.2017.8268998

Ya-Jun Hu, Li-Juan Liu, Chuang Ding, Zhenhua Ling, Lirong Dai

{"title":"The USTC system for blizzard machine learning challenge 2017-ES2","authors":"Ya-Jun Hu, Li-Juan Liu, Chuang Ding, Zhenhua Ling, Lirong Dai","doi":"10.1109/ASRU.2017.8268998","DOIUrl":"https://doi.org/10.1109/ASRU.2017.8268998","url":null,"abstract":"The Blizzard Machine Learning Challenge (BMLC) aims to liberate participants from speech-specific processing when building speech synthesis systems. This paper describes the USTC system for the ES2 sub-task in BMLC2017, which requires participants to train a model to directly predict waveforms from linguistic features. We investigate three aspects of waveform modeling when preparing our system for this task. First, two different model structures for waveform modeling, i.e., WaveNet and SampleRNN, are compared on this task. Second, a strategy of using features extracted from waveforms as intermediate representations for waveform modeling is studied. Experimental results show that using low-level features (STFT amplitude spectra) as intermediate representations can achieve similar performance as using high-level features (mel-cepstra and F0). Third, the feasibility of applying WaveNet to wideband speech signals with more than 256 quantization levels is verified by experiments. Finally, a system which adopts STFT amplitude spectra as intermediate representations to model 24kHz speech waveforms with 1024 mu-law quantization levels is submitted for evaluation. The evaluation results of BMLC2017 demonstrate the effectiveness of our proposed methods.","PeriodicalId":290868,"journal":{"name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115675993","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 4

Improving separation of overlapped speech for meeting conversations using uncalibrated microphone array 改进使用未校准麦克风阵列的会议对话中重叠语音的分离

2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) Pub Date : 2017-12-01 DOI: 10.1109/ASRU.2017.8268916

Keisuke Nakamura, R. Gomez

{"title":"Improving separation of overlapped speech for meeting conversations using uncalibrated microphone array","authors":"Keisuke Nakamura, R. Gomez","doi":"10.1109/ASRU.2017.8268916","DOIUrl":"https://doi.org/10.1109/ASRU.2017.8268916","url":null,"abstract":"In this paper, we propose a novel approach of sound source separation for meeting conversations even when using an uncalibrated microphone array. Our method can blindly estimate three parameters for separation, namely Steering Vectors (SVs), speaker indices, and activity periods of each speaker. First, we estimate the number of speakers and SVs by clustering Time Delay Of Arrival (TDOA) of the observed signal and selecting major clusters to compute TDOA-based SVs. Then, speaker indices and activity periods are estimated by thresholding spatial spectrum using estimated SVs, whose threshold is blindly obtained. Finally, we separate overlapped speeches/noise based on dynamic design of noise correlation matrices of the minimum variance distortionless response (MVDR) beamformer using blindly estimated parameters. The proposed algorithm was evaluated in both separation objective measure and recognition correct rate and showed improvements in both single and simultaneous speech scenarios in a reverberant meeting room. Moreover, the blindly estimated parameters improved separation and recognition compared to geometrically obtained parameters.","PeriodicalId":290868,"journal":{"name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130607696","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

Multilingual bottle-neck feature learning from untranscribed speech 从未转录语音中学习多语言瓶颈特征

2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) Pub Date : 2017-12-01 DOI: 10.1109/ASRU.2017.8269009

Hongjie Chen, C. Leung, Lei Xie, B. Ma, Haizhou Li

引用次数: 32

Noise-robust exemplar matching for rescoring query-by-example search 用于逐例查询搜索记录的噪声鲁棒样本匹配

2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) Pub Date : 2017-12-01 DOI: 10.1109/ASRU.2017.8268909

Emre Yilmaz, Julien van Hout, H. Franco

引用次数: 1

Sequence training of DNN acoustic models with natural gradient 自然梯度DNN声学模型的序列训练

2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) Pub Date : 2017-12-01 DOI: 10.1109/ASRU.2017.8268933

Adnan Haider, P. Woodland

引用次数: 6

Meeting recognition with asynchronous distributed microphone array 采用异步分布式麦克风阵列进行会议识别

2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) Pub Date : 2017-12-01 DOI: 10.1109/ASRU.2017.8268913

S. Araki, Nobutaka Ono, K. Kinoshita, Marc Delcroix

引用次数: 16

JHU Kaldi system for Arabic MGB-3 ASR challenge using diarization, audio-transcript alignment and transfer learning JHU Kaldi系统用于阿拉伯语MGB-3 ASR挑战，使用拨号，音频转录对齐和迁移学习

2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) Pub Date : 2017-12-01 DOI: 10.1109/ASRU.2017.8268956

Vimal Manohar, Daniel Povey, S. Khudanpur

引用次数: 43

Unsupervised HMM posteriograms for language independent acoustic modeling in zero resource conditions 零资源条件下语言无关声学建模的无监督HMM后图

2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) Pub Date : 2017-12-01 DOI: 10.1109/ASRU.2017.8269014

T. Ansari, Rajath Kumar, Sonali Singh, Sriram Ganapathy, V. Devi

{"title":"Unsupervised HMM posteriograms for language independent acoustic modeling in zero resource conditions","authors":"T. Ansari, Rajath Kumar, Sonali Singh, Sriram Ganapathy, V. Devi","doi":"10.1109/ASRU.2017.8269014","DOIUrl":"https://doi.org/10.1109/ASRU.2017.8269014","url":null,"abstract":"The task of language independent acoustic unit modeling in unlabeled raw speech (zero-resource setting) has gained significant interest over the recent years. The main challenge here is the extraction of acoustic representations that elicit good similarity between the same words or linguistic tokens spoken by different speakers and to derive these representations in a language independent manner. In this paper, we explore the use of Hidden Markov Model (HMM) based posteriograms for unsupervised acoustic unit modeling. The states of the HMM (which represent the language independent acoustic units) are initialized using a Gaussian mixture model (GMM) — Universal Background Model (UBM). The trained HMM is subsequently used to generate a temporally contiguous state alignment which are then modeled in a hybrid deep neural network (DNN) model. For the purpose of testing, we use the frame level HMM state posteriors obtained from the DNN as features for the ZeroSpeech challenge task. The minimal pair ABX error rate is measured for both the within and across speaker pairs. With several experiments on multiple languages in the ZeroSpeech corpus, we show that the proposed HMM based posterior features provides significant improvements over the baseline system using MFCC features (average relative improvements of 25% for within speaker pairs and 40% for across speaker pairs). Furthermore, the experiments where the target language is not seen training illustrate the proposed modeling approach is capable of learning global language independent representations.","PeriodicalId":290868,"journal":{"name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","volume":"447 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125776955","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 14

Feature optimized DPGMM clustering for unsupervised subword modeling: A contribution to zerospeech 2017 无监督子词建模的特征优化DPGMM聚类:对zerospeech 2017的贡献

2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) Pub Date : 2017-12-01 DOI: 10.1109/ASRU.2017.8269011

Michael Heck, S. Sakti, Satoshi Nakamura

{"title":"Feature optimized DPGMM clustering for unsupervised subword modeling: A contribution to zerospeech 2017","authors":"Michael Heck, S. Sakti, Satoshi Nakamura","doi":"10.1109/ASRU.2017.8269011","DOIUrl":"https://doi.org/10.1109/ASRU.2017.8269011","url":null,"abstract":"This paper describes our unsupervised subword modeling pipeline for the zero resource speech challenge (ZeroSpeech) 2017. Our approach is built around the Dirichlet process Gaussian mixture model (DPGMM) that we use to cluster speech feature vectors into a dynamically sized set of classes. By considering each class an acoustic unit, speech can be represented as sequence of class posteriorgrams. We enhance this method by automatically optimizing the DPGMM sampler's input features in a multi-stage clustering framework, where we unsupervisedly learn transformations using LDA, MLLT and (basis) fMLLR to reduce variance in the features. We show that this optimization considerably boosts the subword modeling quality, according to the performance on the ABX phone discriminability task. For the first time, we apply inferred subword models to previously unseen data from a new set of speakers. We demonstrate our method's good generalization and the effectiveness of its blind speaker adaptation in extensive experiments on a multitude of datasets. Our pipeline has very little need for hyper-parameter adjustment and is entirely unsupervised, i.e., it only takes raw audio recordings as input, without requiring any pre-defined segmentation, explicit speaker IDs or other meta data.","PeriodicalId":290868,"journal":{"name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","volume":"6 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128294116","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 49