NHSS: A speech and singing parallel database
We present a database of parallel recordings of speech and singing, collected and released
by the Human Language Technology (HLT) laboratory at the National University of …
by the Human Language Technology (HLT) laboratory at the National University of …
Knowledge distillation from bert transformer to speech transformer for intent classification
End-to-end intent classification using speech has numerous advantages compared to the
conventional pipeline approach using automatic speech recognition (ASR), followed by …
conventional pipeline approach using automatic speech recognition (ASR), followed by …
Sonority measurement using system, source, and suprasegmental information
B Sharma, SRM Prasanna - IEEE/ACM Transactions on Audio …, 2016 - ieeexplore.ieee.org
Sonorant sounds are characterized by regions with a prominent formant structure, high
energy, and high degree of periodicity. In this work, the vocal-tract system, excitation source …
energy, and high degree of periodicity. In this work, the vocal-tract system, excitation source …
[PDF][PDF] Scope of Sonority Information in Statistical Parametric Speech Synthesis
B Sharma - isca-students.org
Statistical parametric speech synthesis (SPSS) has been widely used due to its advantages
like flexibility in terms of adaptation of speakers, emotions, lower footprint, robustness …
like flexibility in terms of adaptation of speakers, emotions, lower footprint, robustness …