標(biāo)題: Titlebook: Advances in Speech and Language Technologies for Iberian Languages; IberSPEECH 2014 Conf Juan Luis Navarro Mesa,Alfonso Ortega,Doroteo T. T [打印本頁(yè)] 作者: Causalgia 時(shí)間: 2025-3-21 19:17
書目名稱Advances in Speech and Language Technologies for Iberian Languages影響因子(影響力)
書目名稱Advances in Speech and Language Technologies for Iberian Languages影響因子(影響力)學(xué)科排名
書目名稱Advances in Speech and Language Technologies for Iberian Languages網(wǎng)絡(luò)公開度
書目名稱Advances in Speech and Language Technologies for Iberian Languages網(wǎng)絡(luò)公開度學(xué)科排名
書目名稱Advances in Speech and Language Technologies for Iberian Languages被引頻次
書目名稱Advances in Speech and Language Technologies for Iberian Languages被引頻次學(xué)科排名
書目名稱Advances in Speech and Language Technologies for Iberian Languages年度引用
書目名稱Advances in Speech and Language Technologies for Iberian Languages年度引用學(xué)科排名
書目名稱Advances in Speech and Language Technologies for Iberian Languages讀者反饋
書目名稱Advances in Speech and Language Technologies for Iberian Languages讀者反饋學(xué)科排名
作者: 熱情贊揚(yáng) 時(shí)間: 2025-3-21 20:24
Bei He,Gang Liu,Ying Ji,Yongsheng Si,Rui Gaois. We show that the acoustic differences due to variations in the window length are audible. The experiments reveal an overall preference towards short analysis windows, although longer windows seem to alleviate some artifacts related to training data scarcity.作者: cocoon 時(shí)間: 2025-3-22 00:44 作者: MELD 時(shí)間: 2025-3-22 04:48
Conference proceedings 2014The 29 papers presented were carefully reviewed and selected from 60 submissions. The papers are organized in topical sections on speech production, analysis, coding and synthesis; speaker and language characterization; automatic speech recognition; speech of language technologies in different application fields.作者: 粗鄙的人 時(shí)間: 2025-3-22 12:00 作者: 顯示 時(shí)間: 2025-3-22 13:04 作者: 軍火 時(shí)間: 2025-3-22 19:22
https://doi.org/10.1007/978-3-319-13623-3Automatic speech recognition; Speaker and language characterization; data hiding; deep learning; documen作者: 大吃大喝 時(shí)間: 2025-3-22 23:40
978-3-319-13622-6Springer International Publishing Switzerland 2014作者: CRAFT 時(shí)間: 2025-3-23 03:08 作者: 量被毀壞 時(shí)間: 2025-3-23 06:48 作者: ALB 時(shí)間: 2025-3-23 13:07 作者: 沒收 時(shí)間: 2025-3-23 17:12 作者: 整潔 時(shí)間: 2025-3-23 19:45 作者: synovitis 時(shí)間: 2025-3-24 00:22 作者: Anticoagulant 時(shí)間: 2025-3-24 02:40 作者: Inflated 時(shí)間: 2025-3-24 08:31 作者: ESPY 時(shí)間: 2025-3-24 13:35 作者: 配置 時(shí)間: 2025-3-24 14:59 作者: 正式演說 時(shí)間: 2025-3-24 19:49
Dong Liu,Miao Yu,Nan Sun,Ying Qiwn to be a good choice to encode in a compact way alternative decoding hypotheses from a speech recognition system. These are typically used for the spoken term detection and keyword-spotting tasks, where a phoneme sequence query is matched to a reference lattice. Most current approaches suffer from作者: TOXIN 時(shí)間: 2025-3-25 01:50 作者: Obstacle 時(shí)間: 2025-3-25 03:55
Xuechun Wang,Jun Li,Shishun Taonefit is still being taken from this feature for noise-robust automatic speech recognition (ASR). In this paper we propose a novel system to estimate missing-data masks for robust ASR on dual-microphone smartphones. This novel system is based on deep neural networks (DNNs), which have proven to be a作者: critic 時(shí)間: 2025-3-25 08:57
Zhenqi Fan,Chunjing Si,Quanli Yangectures. In this work, we propose a simple yet effective language model adaptation technique based on document retrieval from the web. This technique is combined with slide adaptation, and compared against a strong baseline language model and a stronger slide-adapted baseline. These adaptation techn作者: innovation 時(shí)間: 2025-3-25 14:38 作者: 思想上升 時(shí)間: 2025-3-25 18:23 作者: 借喻 時(shí)間: 2025-3-25 23:39 作者: nascent 時(shí)間: 2025-3-26 03:47
Zhiwei Zheng,Liuyan Yu,Xiushui Liuorts from the Spanish public broadcast channel (RTVE). In the CM computation, first Acoustic-Phonetic Decoding (APD) is carried out, then we align reference and hypothesis word sequences through a phone-graph, and finally in this decoding mesh given a time interval, the maximum posterior probability作者: 整理 時(shí)間: 2025-3-26 06:51
Shan Zhao,Guifen Chen,Siwei Fu,Enze Xiaoopean Portuguese for distant voice command recognition applications in domestic environments. The analysis, conducted in a multi-channel multi-room scenario, showed the importance of adequate room detection and channel selection strategies to obtain acceptable performances. Two different computation作者: Estimable 時(shí)間: 2025-3-26 10:51
0302-9743 m 60 submissions. The papers are organized in topical sections on speech production, analysis, coding and synthesis; speaker and language characterization; automatic speech recognition; speech of language technologies in different application fields.978-3-319-13622-6978-3-319-13623-3Series ISSN 0302-9743 Series E-ISSN 1611-3349 作者: 同謀 時(shí)間: 2025-3-26 14:03 作者: BILE 時(shí)間: 2025-3-26 17:14 作者: 新陳代謝 時(shí)間: 2025-3-26 21:00
Haiyan Hu,Huoguo Zheng,Shihong Liud Total Variability (i-vector) strategies, respectively. Moreover, a simple fusion of the developed approaches and the reference systems has been performed. Some individual and fusion systems outperform the reference systems, obtaining ~ 17% of relative improvement in terms of .. for one of the challenging pairs.作者: Canyon 時(shí)間: 2025-3-27 01:15
Hongxu Wang,FuJin Zhang,Yunsheng Xufor acoustic modeling in a noisy automatic speech recognition environment. Experiments show that DMNs improve substantially the recognition accuracy over DNNs and other traditional techniques in both clean and noisy conditions on the TIMIT dataset.作者: 媒介 時(shí)間: 2025-3-27 09:18
Zhenqi Fan,Chunjing Si,Quanli Yangiques are compared within two different acoustic models: a standard HMM model and the CD-DNN-HMM model. The proposed method obtains improvements on WER of up to 14% relative with respect to a competitive baseline as well as outperforming slide adaptation.作者: 制定法律 時(shí)間: 2025-3-27 12:18 作者: Harridan 時(shí)間: 2025-3-27 16:32 作者: 人類的發(fā)源 時(shí)間: 2025-3-27 19:18
Unsupervised Accent Modeling for Language Identificationing the test, each utterance is evaluated against all of them. The highest score of each language is selected to make decisions. The experiment was carried out on 6 languages of the 2011 NIST LRE dataset. For the 30 s condition, the relative improvement over the baseline was of 11%.作者: 憤怒歷史 時(shí)間: 2025-3-27 22:59 作者: indoctrinate 時(shí)間: 2025-3-28 04:58
Confidence Measures in Automatic Speech Recognition Systems for Error Detection in Restricted Domainate the reliability of recognition results, discarding low confidence words at the output. These CM can be used as a tool for Unsupervised Learning Techniques, and also for helping human supervision of recognition results. If accurate enough, these CM would increase the usability as well as the robustness of speech applications.作者: 真繁榮 時(shí)間: 2025-3-28 08:54
Recognition of Distant Voice Commands for Home Applications in Portuguesehow that the strategies based on envelope-variance measure consistently outperformed the remaining methods investigated, and particularly, that channel selection strategies can be more convenient than baseline beamforming methods, such as delay-and-sum, for this type of multi-room scenarios.作者: Antecedent 時(shí)間: 2025-3-28 13:55 作者: OMIT 時(shí)間: 2025-3-28 17:04
https://doi.org/10.1007/978-3-319-48354-2across the AHC iterations is done using reference speaker ground-truth labels to select the purer clustering as input for the global framework. Experiments on the REPERE phase 1 test database show improvements of around 6% absolute DER compared to the baseline system output.作者: 榨取 時(shí)間: 2025-3-28 19:47 作者: Systemic 時(shí)間: 2025-3-29 00:12
Xiaobin Qiu,Hongqian Chen,Nan Zhoud. All processing is done locally on the phone, which is able to react in real-time to incoming keywords. In this paper we describe the application, review the matching algorithm we used and show experimentally that it successfully reacts to voice commands in a variety of acoustic conditions.作者: sparse 時(shí)間: 2025-3-29 06:08
Global Speaker Clustering towards Optimal Stopping Criterion in Binary Key Speaker Diarizationacross the AHC iterations is done using reference speaker ground-truth labels to select the purer clustering as input for the global framework. Experiments on the REPERE phase 1 test database show improvements of around 6% absolute DER compared to the baseline system output.作者: saturated-fat 時(shí)間: 2025-3-29 11:14
CVX-Optimized Beamforming and Vector Taylor Series Compensation with German ASR Employing Star-Shapedium-vocabulary German database for microphone array made of embedded clean signals contaminated with real room impulsive responses and mixed in a ‘natural’ way with real noises. We show that the proposed enhancement framework performs better than other related systems on the presented database.作者: blithe 時(shí)間: 2025-3-29 13:35
Flexible Stand-Alone Keyword Recognition Application Using Dynamic Time Warpingd. All processing is done locally on the phone, which is able to react in real-time to incoming keywords. In this paper we describe the application, review the matching algorithm we used and show experimentally that it successfully reacts to voice commands in a variety of acoustic conditions.作者: 教唆 時(shí)間: 2025-3-29 19:37
Statistical Text-to-Speech Synthesis of Spanish Subtitlesthe best of our knowledge, this is the first time that a DNN-based TTS system has been implemented for the synthesis of Spanish. A comparative objective evaluation between both models has been carried out. Our results show that DNN-based systems can reconstruct speech waveforms more accurately.作者: 兇殘 時(shí)間: 2025-3-29 20:50
Unsupervised Training of PLDA with Variational Bayesre latent variables. We experimented on unlabeled NIST SRE data. The trained models were evaluated on NIST SRE10. Compared to cosine distance, unsupervised PLDA improved EER by 28% and minimum DCF by 36%.作者: Interferons 時(shí)間: 2025-3-30 02:32 作者: MODE 時(shí)間: 2025-3-30 06:08 作者: PON 時(shí)間: 2025-3-30 11:51 作者: decipher 時(shí)間: 2025-3-30 16:12 作者: 責(zé)任 時(shí)間: 2025-3-30 19:50
Hailiang Zhang,Xudong Sun,Yande Liumpared. The quantitative framework revealed itself capable of dealing with the data for the /l/, allowing a systematic analysis of the multiple realisations. The results regarding syllable position effects and coarticulation of /l/ with adjacent vowels are in line with previous findings.作者: crutch 時(shí)間: 2025-3-30 21:36
https://doi.org/10.1007/978-3-319-48357-3ing the test, each utterance is evaluated against all of them. The highest score of each language is selected to make decisions. The experiment was carried out on 6 languages of the 2011 NIST LRE dataset. For the 30 s condition, the relative improvement over the baseline was of 11%.作者: Dri727 時(shí)間: 2025-3-31 04:31 作者: muffler 時(shí)間: 2025-3-31 06:26 作者: 一再遛 時(shí)間: 2025-3-31 12:14 作者: OATH 時(shí)間: 2025-3-31 16:37 作者: Isolate 時(shí)間: 2025-3-31 20:57 作者: 并排上下 時(shí)間: 2025-4-1 00:18 作者: 去掉 時(shí)間: 2025-4-1 03:21 作者: 物質(zhì) 時(shí)間: 2025-4-1 07:21 作者: tendinitis 時(shí)間: 2025-4-1 12:02
Global Impostor Selection for DBNs in Multi-session i-Vector Speaker Recognitionhe proposed selection method improves the performance of the DBN-based system in terms of minDCF by 7% and the whole system outperforms the baseline in the challenge by more than 22% relative improvement... Speaker Recognition, Deep Belief Network, Impostor Selection, NIST i-vector challenge.作者: 衰老 時(shí)間: 2025-4-1 15:52
Phoneme-Lattice to Phoneme-Sequence Matching Algorithm Based on Dynamic Programmingd per arc, instead of likelihoods and an acoustic matching distance is combined with the edit distance at every arc. Finally, total matching scores are normalized based on the length of the optimum alignment path. The resulting algorithm is compared to a state-of-the-art phoneme-lattice-to-string ma作者: 古老 時(shí)間: 2025-4-1 20:35
Advances in Speech and Language Technologies for Iberian LanguagesIberSPEECH 2014 Conf作者: disrupt 時(shí)間: 2025-4-2 01:31 作者: pus840 時(shí)間: 2025-4-2 05:34 作者: Gingivitis 時(shí)間: 2025-4-2 08:21
Analysis and Synthesis of Emotional Speech in Spanish for the Chat Domainof read aloud chat messages, and explores the application of the obtained results to generate emotional synthetic speech using a novel parametric approach. The obtained results show that the analysed parameters seem to be relevant for the differentiation among the considered emotions, but that its u作者: objection 時(shí)間: 2025-4-2 12:15
