• Decoder for large vocabulary continuous speech recognition ◦word conditioned tree search (supporting across-word models) ◦optimized HMM emission probability calculation using SIMD instructions ◦refined acoustic pruning using language model lookahead ◦word lattice generation • Feature extraction ◦a flexible framework for data processing: Flow ◦MFCC features ◦PLP features ◦Gammatone features ◦voicedness feature ◦vocal tract length normalization (VTLN) ◦support for several feature dimension reduction methods (e.g. LDA, PCA) ◦easy implementation of new features as well as easy integration of external features using Flow networks • Acoustic modeling ◦Gaussian mixture distributions for HMM emission probabilities ◦phoneme in triphone context (or shorter context) ◦across-word context dependency of phonemes ◦allophone parameter tying using phonetic decision trees (classification and regression trees, CART) ◦globally pooled diagonal covariance matrix (other types of covariance modelling are possible, but not fully tested) ◦maximum likelihood training ◦discriminative training (minimum phone error (MPE) criterion) ◦linear algebra support using LAPACK, BLAS • Language modeling ◦support for language models in ARPA format ◦weighted grammars (weighted finite state automaton) • Neural networks (new in v0.6) ◦training of arbitrarily deep feed-forward networks ◦CUDA support for running on GPUs ◦OpenMP support for running on CPUs ◦variety of activation functions, training criteria and optimization algorithms ◦sequence discriminative training, e.g. MMI or MPE (new in v0.7) ◦integration in feature extraction pipeline ("Tandem approach") ◦integration in search and lattice processing pipeline ("Hybrid NN/HMM approach") • Speaker adaptation ◦Constrained MLLR (CMLLR, "feature space MLLR", fMLLR) ◦Unsupervised maximum likelihood linear regression mean adaptation (MLLR) ◦speaker / segment clustering using Bayesian Information Criterion (BIC) as stop criterion • Lattice processing ◦n-best list generation ◦confusion network generation and decoding ◦lattice rescoring ◦lattice based system combination •input / output formats ◦nearly all input and output data is in easily process-able XML or plain text formats ◦converter tools for the generation of NIST file formats are included ◦HTK lattice format ◦converter tools for HTK models

• Multiple platforms: Runs on numerous platforms and operating systems from small embedded to large server systems. • Neural network technology: Provides accurate speaker-independent speech recognition, even in noisy environments. • Efficient memory and CPU usage: Operates within memory and MIPs constraints or runs many concurrent channels on a server system. See the product specification sheet for details. • Multiple languages: Is available in U.S. and U.K. English, Canadian and European French, German, Japanese, Korean, Castilian and Latin American Spanish, Swedish and Italian. • Phonetic component: Aligns word phonetics with audio data, enabling animators to synchronize a character's facial movements with the phonetic components of speech. Realistic facial movements are the result as animated characters "speak."