DATA PROCESSING: SPEECH SIGNAL PROCESSING, LINGUISTICS, LANGUAGE TRANSLATION, AND AUDIO COMPRESSION/DECOMPRESSION

Sub-classifications for 704
ClassificationsCodeApplicationsSubscribe
 
LINGUISTICS704/0010000
 
Translation machine704/0020000
 
Having particular Input/Output device704/0030000
 
Based on phrase, clause, or idiom704/0040000
 
For partial translation704/0050000
 
Punctuation704/0060000
 
Storage or retrieval of data704/0070001
 
Multilingual or national language support704/0080000
 
Natural language704/0090002
 
Dictionary building, modification, or prioritization704/0100000
 
SPEECH SIGNAL PROCESSING704/2000000
 
Psychoacoustic704/2001000
 
For storage or transmission704/2010000
 
Neural network704/2020000
 
Transformation704/2030000
 
Orthogonal functions704/2040000
 
Frequency704/2050000
 
Specialized information704/2060000
 
Pitch704/2070000
 
Voiced or unvoiced704/2080000
 
Formant704/2090000
 
Silence decision704/2100000
 
Time704/2110000
 
Pulse code modulation (PCM)704/2120000
 
Zero crossing704/2130000
 
Voiced or unvoiced704/2140000
 
Silence decision704/2150000
 
Correlation function704/2160000
 
Autocorrelation704/2170000
 
Cross-correlation704/2180000
 
Linear prediction704/2190000
 
Analysis by synthesis704/2200000
 
Pattern matching vocoders704/2210000
 
Vector quantization704/2220000
 
Excitation patterns704/2230000
 
Normalizing704/2240000
 
Gain control704/2250000
 
Noise704/2260000
 
Pretransmission704/2270000
 
Post-transmission704/2280000
 
Adaptive bit allocation704/2290000
 
Quantization704/2300000
 
Recognition704/2310000
 
Neural network704/2320000
 
Detect speech in noise704/2330001
 
Normalizing704/2340000
 
Speech to image704/2350003
 
Specialized equations or comparisons704/2360000
 
Correlation704/2370000
 
Distance704/2380000
 
Similarity704/2390000
 
Probability704/2400001
 
Dynamic time warping704/2410000
 
Viterbi trellis704/2420000
 
Creating patterns for matching704/2430000
 
Update patterns704/2440000
 
Clustering704/2450000
 
Voice recognition704/2460002
 
Preliminary matching704/2470000
 
Endpoint detection704/2480000
 
Subportions704/2490000
 
Specialized models704/2500000
 
Word recognition704/2510000
 
Preliminary matching704/2520000
 
Endpoint detection704/2530000
 
Subportions704/2540000
 
Specialized models704/2550000
 
Markov704/2560000
 
Hidden Markov Model (HMM) (EPO)704/2561000
 
Training of HMM (EPO)704/2562000
 
With insufficient amount of training data, e.g., state sharing, tying, deleted interpolation (EPO)704/2563000
 
Duration modeling in HMM, e.g., semi HMM, segmental models, transition probabilities (EPO)704/2564000
 
Hidden Markov (HM) network (EPO)704/2565000
 
State emission probability (EPO)704/2566000
 
Continuous density, e.g, Gaussian distribution, Lapalce (EPO)704/2567000
 
Discrete density, e.g., Vector Quantization preprocessor, look up tables (EPO)704/2568000
 
Natural language704/2570001
 
Synthesis704/2580000
 
Neural network704/2590000
 
Image to speech704/2600000
 
Vocal tract model704/2610000
 
Linear prediction704/2620000
 
Correlation704/2630000
 
Excitation704/2640000
 
Interpolation704/2650000
 
Specialized model704/2660000
 
Time element704/2670000
 
Frequency element704/2680000
 
Transformation704/2690000
 
Application704/2700000
 
Speech assisted network704/2701000
 
Handicap aid704/2710000
 
Novelty item704/2720000
 
Security system704/2730000
 
Warning/alarm system704/2740000
 
Speech controlled system704/2750000
 
Pattern display704/2760000
 
Translation704/2770000
 
Sound editing704/2780000
 
AUDIO SIGNAL BANDWIDTH COMPRESSION OR EXPANSION704/5000000
 
With content reduction encoding704/5010000
 
Delay line704/5020000
 
AUDIO SIGNAL TIME COMPRESSION OR EXPANSION (E.G., RUN LENGTH CODING)704/5030000
 
With content reduction encoding704/5040000
 
SPEAKER IDENTIFICATION OR VERIFICATION (EPO)704/E170010
 
Recognition of special voice characteristics, e.g., for use in a lie detector; recognition of animal voices, etc. (EPO)704/E170020
 
Systems using speaker recognizers (EPO)704/E170030
 
Details (EPO)704/E170040
 
Preprocessing operations, e.g., segment selection, etc., pattern representation or modeling, e.g., based on linear discriminant analysis (LDA), principal components, etc.; feature selection or extraction (EPO)704/E170050
 
Training, model building, enrollment (EPO)704/E170060
 
Decision making techniques, pattern matching strategies (EPO)704/E170070
 
Use of particular distance or distortion metric between probe pattern and reference templates (EPO)704/E170080
 
Multimodal systems, i.e., based on the integration of multiple recognition engines or experts fusion (EPO)704/E170090
 
Score normalization (EPO)704/E170100
 
Use of phonemic categorization or speech recognition prior to speaker recognition or verification (EPO)704/E170110
 
Hidden Markov Models (HMMs) (EPO)704/E170120
 
Artificial neural networks, connectionist approaches (EPO)704/E170130
 
Pattern transformations and operations aimed at increasing system robustness, e.g., against channel noise, different working conditions, etc. (EPO)704/E170140
 
Interactive procedures, man-machine interface (EPO)704/E170150
 
User prompted to utter a password or predefined text (EPO)704/E170160
 
SPEECH RECOGNITION (EPO)704/E150011
 
Assessment or evaluation of speech recognition systems (EPO)704/E150020
 
Language recognition (EPO)704/E150030
 
Feature extraction for speech recognition; selection of recognition unit (EPO)704/E150041
 
Segmentation or word limit detection (EPO)704/E150050
 
Word boundary detection (EPO)704/E150060
 
Creation of reference templates; training of speech recognition systems, e.g., adaption to the characteristics of the speaker's voice, etc. (EPO)704/E150070
 
Training (EPO)704/E150080
 
Adaptation (EPO)704/E150090
 
In the frequency domain (EPO)704/E150100
 
To speaker (EPO)704/E150110
 
Supervised, i.e., under machine guidance (EPO)704/E150120
 
Unsupervised (EPO)704/E150130
 
Speech classification or search (EPO)704/E150140
 
Using distance or distortion measures between unknown speech and reference templates (EPO)704/E150150
 
Using dynamic programming techniques, e.g., Dynamic Time Warping (DTW), etc. (EPO)704/E150160
 
Using artificial neural networks (EPO)704/E150170
 
Using natural language modeling (EPO)704/E150180
 
Using context dependencies, e.g., language models, etc. (EPO)704/E150190
 
Phonemic context, e.g., pronunciation rules, phonotactical constraints, phoneme n-grams, etc. (EPO)704/E150200
 
Grammatical context, e.g., disambiguation of the recognition hypotheses based on word sequence rules, etc. (EPO)704/E150210
 
Formal grammars, e.g., finite state automata, context free grammars, word networks, etc. (EPO)704/E150220
 
Probabilistic grammars, e.g., word n-grams, etc. (EPO)704/E150230
 
Semantic context, e.g., disambiguation of the recognition hypotheses based on word meaning, etc. (EPO)704/E150240
 
Using prosody or stress (EPO)704/E150250
 
Parsing for meaning understanding (EPO)704/E150260
 
Using statistical models, e.g., Hidden Markov Models (HMMs), etc. (EPO)704/E150270
 
Hidden Markov Models (HMMs) (EPO)704/E150280
 
Training of Hidden Markov Models (HMMs) (EPO)704/E150290
 
With insufficient amount of training data, e.g., state sharing, tying, deleted interpolation, etc. (EPO)704/E150300
 
Duration modeling in Hidden Markov Models (HMMs), e.g., semi-HMM, segmental models, transition probabilities, etc. (EPO)704/E150310
 
Hidden Markov Models (HMMs) network (EPO)704/E150320
 
State emission probabilities (EPO)704/E150330
 
Continuous densities, e.g., Gaussian distribution, Laplace, etc. (EPO)704/E150340
 
Discrete densities, e.g., Vector Quantization preprocessor, look-up tables, etc. (EPO)704/E150350
 
Neural Network (NN) as output probability estimator, e.g., hybrid HMM/NN, etc. (EPO)704/E150360
 
Non-hidden Markov Model (EPO)704/E150370
 
Recognition networks (EPO)704/E150380
 
Speech recognition techniques for robustness in adverse environments, e.g., in noise, of stress induced speech, etc. (EPO)704/E150390
 
Procedures used during a speech recognition process, e.g., man-machine dialogue, etc. (EPO)704/E150400
 
Speech recognition using nonacoustical features, e.g., position of the lips, etc. (EPO)704/E150410
 
Using position of the lips, movement of the lips, or face analysis (EPO)704/E150420
 
Speech to text systems (EPO)704/E150431
 
Speech recognition depending on application context, e.g., in a computer, etc. (EPO)704/E150440
 
Systems using speech recognizers (EPO)704/E150450
 
Constructional details of speech recognition systems (EPO)704/E150460
 
Distributed recognition, e.g., in client-server systems for mobile phones or network applications, etc. (EPO)704/E150470
 
Memory allocation or algorithm optimization to reduce hardware requirements (EPO)704/E150480
 
Multiple recognizers used in sequence or in parallel; corresponding voting or score combination systems (EPO)704/E150490
 
Recognizers for parallel processing (EPO)704/E150500
 
SPEECH OR AUDIO SIGNAL ANALYSIS-SYNTHESIS TECHNIQUES FOR REDUNDANCY REDUCTION, E.G., IN VOCODERS, ETC.; CODING OR DECODING OF SPEECH OR AUDIO SIGNALS; COMPRESSION OR EXPANSION OF SPEECH OR AUDIO SIGNALS, E.G., SOURCE-FILTER MODELS, PSYCHOACOUSTIC ANALYSIS, ETC. (EPO)704/E190010
 
Perceptual measures for quality assessment (EPO)704/E190020
 
Correction of errors induced by the transmission channel, if related to the coding (EPO)704/E190030
 
Lossless audio signal coding; perfect reconstruction of coded audio signal by transmission of coding error (EPO)704/E190040
 
Multichannel audio signal coding and decoding, i.e., using interchannel correlation to reduce redundancies, e.g., joint-stereo, intensity-coding, matrixing, etc. (EPO)704/E190050
 
Comfort noise, silence coding (EPO)704/E190060
 
Speech coding using phonetic or linguistical decoding of the source; reconstruction using text-to-speech synthesis (EPO)704/E190070
 
Systems using vocoders (EPO)704/E190080
 
Audio watermarking, i.e., embedding inaudible data in the audio signal (EPO)704/E190090
 
Using spectral analysis, e.g., transform vocoders, subband vocoders, perceptual audio coders, psychoacoustically based lossy encoding, etc., e.g., MPEG audio, Dolby AC-3, etc. (EPO)704/E190100
 
Blocking, i.e., grouping of samples in time, choice of analysis window, overlap factor (EPO)704/E190110
 
Detection of transients and attacks for time/frequency resolution switching (EPO)704/E190120
 
Noise substitution, i.e., substituting nontonal spectral components by noisy source (EPO)704/E190130
 
Spectral prediction for pre-echo prevention; temporal noise shaping (TNS), e.g., in MPEG2 or MPEG4, etc. (EPO)704/E190140
 
Quantization or dequantization of spectral components (EPO)704/E190150
 
Scalar quantization (EPO)704/E190160
 
Vector quantization, e.g., Twin-VQ audio, etc. (EPO)704/E190170
 
Using subband decomposition (EPO)704/E190180
 
Subband vocoders (EPO)704/E190190
 
Using orthogonal transformation (EPO)704/E190200
 
Using wavelet decomposition (EPO)704/E190210
 
Dynamic bit allocation (EPO)704/E190220
 
Using predictive techniques; codecs based on source-filter modelization (EPO)704/E190230
 
Determination or coding of the spectral characteristics, e.g., of the short-term prediction coefficients, etc. (EPO)704/E190240
 
Line spectrum pair (LSP) vocoders (EPO)704/E190250
 
Determination or coding of the excitation function; determination or coding of the long-term prediction characteristics (EPO)704/E190260
 
Determination or coding of an excitation gain (EPO)704/E190270
 
Using mixed excitation model, e.g., MELP, MBE, Split band LPC, HVXC, etc. (EPO)704/E190280
 
Long-term prediction, i.e., removing periodical redundancies, e.g., adaptive codebook, pitch predictor, etc. (EPO)704/E190290
 
Using sinusoidal excitation model (EPO)704/E190300
 
Using prototype waveform decomposition or waveform interpolative coders (PWI) (EPO)704/E190310
 
Determination or coding of a multipulse excitation (EPO)704/E190320
 
Algebraic codebook; sparse pulse excitation (EPO)704/E190330
 
Regular pulse excitation (EPO)704/E190340
 
Determination or coding of a code excitation; code excited linear prediction (CELP) vocoders (EPO)704/E190350
 
Pitch excitation, e.g., PSI-CELP (pitch synchronous innovation CELP), etc. (EPO)704/E190360
 
Residual excited linear prediction (RELP) (EPO)704/E190370
 
Vector sum excited linear prediction (VSELP) (EPO)704/E190380
 
Details of speech and audio coders (EPO)704/E190390
 
Vocoder architecture (EPO)704/E190400
 
Vocoders using multiple modes (EPO)704/E190410
 
Using sound class specific coding, hybrid encoders, object-based coding (EPO)704/E190420
 
Mode decision, i.e., based on audio signal content versus external parameter (EPO)704/E190430
 
Variable rate or variable quality codecs, e.g., scalable representation encoding, etc. (EPO)704/E190440
 
Pre- or post-filtering (EPO)704/E190450
 
Pre-filtering, e.g., high frequency emphasis prior to encoding, etc. (EPO)704/E190460
 
Post-filtering, e.g., pitch enhancement, formant emphasis for decoder, etc. (EPO)704/E190470
 
Audio streaming, i.e., formatting and decoding of an encoded audio signal (EPO)704/E190480
 
Transcoding, i.e., converting between two coded representations avoiding cascaded coding-decoding (EPO)704/E190490
 
MODIFICATION OF AT LEAST ONE CHARACTERISTIC OF SPEECH WAVES (EPO)704/E210010
 
Speech enhancement, e.g., noise reduction, echo cancellation, etc. (EPO)704/E210020
 
Applications (EPO)704/E210030
 
Speech corrupted by noise (EPO)704/E210040
 
Periodic noise (EPO)704/E210050
 
The noise being separate speech (EPO)704/E210060
 
Speech corrupted by echo-reverberation (EPO)704/E210070
 
Speech corrupted by stress-Lombard effect (EPO)704/E210080
 
Enhancement of intelligibility of clean or coded speech (EPO)704/E210090
 
Enhancement of diverse speech (EPO)704/E210100
 
Bandwidth extension taking place at the receiving side, e.g., generation of low- or high-frequency components, regeneration of spectral holes, etc. (EPO)704/E210110
 
Separate reconstruction of interference and of speech signal (EPO)704/E210120
 
The interference being a separate speaker (EPO)704/E210130
 
Active noise canceling (EPO)704/E210140
 
Public address system (EPO)704/E210150
 
Suppression or repetition of time signal segments (EPO)704/E210160
 
Time compression or expansion (EPO)704/E210170
 
Suppression or repetition of time signal segments (EPO)704/E210180
 
Transformation of speech into a nonaudible representation, e.g., speech visualization, speech processing for tactile aids, etc. (EPO)704/E210190
 
Synchronization of speech with image or synthesis of the lips movement from speech, e.g., for "talking heads," etc.(EPO)704/E210200
 
MISCELLANEOUS ANALYSIS OR DETECTION OF SPEECH CHARACTERISTICS (EPO)704/E110010
 
General speech analysis without concrete application (EPO)704/E110020
 
Detection of presence or absence of speech signals (EPO)704/E110030
 
Voice/data decision (EPO)704/E110040
 
End point detection (EPO)704/E110050
 
Pitch determination of speech signals (EPO)704/E110060
 
Voiced-unvoiced decision (EPO)704/E110070
 
SPEECH SYNTHESIS; TEXT TO SPEECH SYSTEMS (EPO)704/E130010
 
Methods for producing synthetic speech; speech synthesizers (EPO)704/E130020
 
Concept-to-speech synthesizers; generation of natural phrases not from text but from machine-based concepts (EPO)704/E130030
 
Sound editing, manipulating voice of the synthesizer (EPO)704/E130040
 
Details of speech synthesis systems, e.g., synthesizer architecture, memory management, etc. (EPO)704/E130050
 
Architecture of speech synthesizers (EPO)704/E130060
 
Excitation (EPO)704/E130070
 
Systems using speech synthesizers (EPO)704/E130080
 
Elementary speech units used in speech synthesizers; concatenation rules (EPO)704/E130090
 
Concatenation (EPO)704/E130100
 
Text analysis, generation of parameters for speech synthesis out of text, e.g., grapheme to phoneme translation, prosody generation, stress, or intonation determination, etc. (EPO)704/E130110
 
Grapheme to phoneme, detection of language (EPO)704/E130120
 
Prosody rules derived from text (EPO)704/E130130
 
Stress or intonation (EPO)704/E130140
 
CLASS-RELATED FOREIGN DOCUMENTS704/FOR0000