Inventor

SORIN ALEXANDER

IL22 patents

⚠️ This page may combine multiple inventors who share the name “SORIN ALEXANDER”. Patents are grouped by organization below to help distinguish them — per-person disambiguation is on the roadmap.

SORIN ALEXANDER

IBM

Computational effectiveness enhancement of frequency domain pitch estimators

System and method for combined frequency-domain and time-domain pitch extraction for speech signals

OCR-based image compression

Coherently-modified speech signal generation by time-dependent scaling of intensity of a pitch-modified utterance

Coherent pitch and intensity modification of speech signals

Restoration of high-order Mel Frequency Cepstral Coefficients

Low-frequency band noise detection

Pitch quantization for distributed speech recognition

Coherent pitch and intensity modification of speech signals

Class quantization for distributed speech recognition

Structure-preserving attention mechanism in sequence-to-sequence neural models

Voice transformation allowance determination and representation

Voice-transformation based data augmentation for prosodic classification

SORIN ALEXANDER

User interface for providing supplemental information

Restoration of high-order Mel frequency cepstral coefficients

Methods and systems of providing supplemental informaton

System and method for automatic prediction of speech suitability for statistical modeling

NUANCE COMMUNICATIONS INC

ASR-aided transcription with segmented feedback training

Remote tracing and debugging of automatic speech recognition servers by speech reconstruction from cepstra and pitch information

Systems and methods for encoding audio signals

CHAZAN DAN

Speech synthesis using complex spectral modeling

SHECHTMAN SLAVA

Statistical enhancement of speech output from a statistical text-to-speech synthesis system