Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 3
Encontrada(s) 1 página(s)

Addi. Archivo Digital para la Docencia y la Investigación
Publicación Contribución de congreso (ConferenceOutput)

Parallel vs. Non-parallel Voice Conversion for Esophageal Speech

  • Serrano García, Luis
  • Raman, Sneha
  • Tavarez Arriba, David
  • Navas Cordón, Eva
  • Hernáez Rioja, Inmaculada
State of the art systems for voice conversion have been shown to generate highly natural sounding converted speech. Voice conversion techniques have also been applied to alaryngeal speech, with the aim of improving its quality or its intelligibility. In this paper, we present an attempt to apply a voice conversion strategy based on phonetic posteriorgrams (PPGs), which produces very high quality converted speech, to improve the characteristics of esophageal speech. The main advantage of this PPG based architecture lies in the fact that it is able to convert speech from any source, without the need to previously train the system with a parallel corpus. However, our results show that the PPG approach degrades the intelligibility of the converted speech considerably, especially when the input speech is already poorly intelligible. In this paper two systems are compared, an LSTM based one-to-one conversion system, which is referred to as the baseline, and the new system using phonetic posteriorgrams. Both spectral parameters and f0 are converted using DNN (Deep Neural Network) based architectures. Results from both objective and subjective evaluations are presented, showing that although ASR (Automated Speech Recognition) errors are reduced, original esophageal speech is still preferred by subjects., This work has been partially funded by the Spanish Ministry of Economy and Competitiveness with FEDER support (RESTORE project, TEC2015-67163-C2-1-R), the Basque Government (BerbaOla project, KK-2018/00014) and from the EUs H2020 research and innovation programme under the MSCA GA 67532*4 (the ENRICH network: www.enrich-etn.eu).
Addi. Archivo Digital para la Docencia y la Investigación
Publicación Contribución de congreso (ConferenceOutput)

Listening to Laryngectomees: A study of Intelligibility and Self-reportedListening Effort of Spanish Oesophageal Speech

  • Raman, Sneha
  • Hernáez Rioja, Inmaculada
  • Navas Cordón, Eva
  • Serrano García, Luis
Oesophageal speakers face a multitude of challenges, such asdifficulty in basic everyday communication and inability to in-teract with digital voice assistants. We aim to quantify the diffi-culty involved in understanding oesophageal speech (in human-human and human-machine interactions) by measuring intel-ligibility and listening effort. We conducted a web-based lis-tening test to collect these metrics. Participants were asked totranscribe and then rate the sentences for listening effort on a5-point Likert scale. Intelligibility, calculated as Word ErrorRate (WER), showed significant correlation with user rated ef-fort. Speaker type (healthy or oesophageal) had a major effecton intelligibility and effort. Listeners familiar with oesophagealspeech did not have any advantage over non familiar listeners incorrectly understanding oesophageal speech. However, they re-ported lesser effort in listening to oesophageal speech comparedto non familiar listeners. Additionally, we calculated speaker-wise mean WERs and they were significantly lower when com-pared to an automatic speech recognition system, This project has received funding from the European UnionsH2020 research and innovation programme under the MarieCurie European Training Network ENRICH (675324).The work has been partially funded by the Spanish Min-istry of Economy and Competitiveness with FEDER support(MINECO/FEDER, UE) (RESTORE project, TEC2015-67163-C2-1-R
Addi. Archivo Digital para la Docencia y la Investigación
Publicación Contribución de congreso (ConferenceOutput)

LSTM based voice conversion for laryngectomees

  • Serrano García, Luis
  • Tavarez Arriba, David
  • Sarasola Aramendia, Xabier
  • Raman, Sneha
  • Saratxaga Couceiro, Ibon
  • Navas Cordón, Eva
  • Hernáez Rioja, Inmaculada
This paper describes a voice conversion system designed withthe aim of improving the intelligibility and pleasantness of oe-sophageal voices. Two different systems have been built, oneto transform the spectral magnitude and another one for thefundamental frequency, both based on DNNs. Ahocoder hasbeen used to extract the spectral information (mel cepstral co-efficients) and a specific pitch extractor has been developed tocalculate the fundamental frequency of the oesophageal voices.The cepstral coefficients are converted by means of an LSTMnetwork. The conversion of the intonation curve is implementedthrough two different LSTM networks, one dedicated to thevoiced unvoiced detection and another one for the predictionof F0 from the converted cepstral coefficients. The experi-ments described here involve conversion from one oesophagealspeaker to a specific healthy voice. The intelligibility of thesignals has been measured with a Kaldi based ASR system. Apreference test has been implemented to evaluate the subjectivepreference of the obtained converted voices comparing themwith the original oesophageal voice. The results show that spec-tral conversion improves ASR while restoring the intonation ispreferred by human listeners, This work has been partially funded by the Spanish Ministryof Economy and Competitiveness with FEDER support (RE-STORE project, TEC2015-67163-C2-1-R), the Basque Govern-ment (BerbaOla project, KK-2018/00014) and from the Euro-pean Unions H2020 research and innovation programme un-der the Marie Curie European Training Network ENRICH(675324).