1    adinrec
2
3ADINREC(1)                  General Commands Manual                 ADINREC(1)
4
5
6

NAME

8           adinrec
9          - record audio device and save one utterance to a file
10

SYNOPSIS

12       adinrec [options...] {filename}
13

DESCRIPTION

15       adinrec opens an audio stream, detects an utterance input and store it
16       to a specified file. The utterance detection is done by level and
17       zero-cross thresholds. Default input device is microphone, but other
18       audio input source, including Julius A/D-in plugin, can be used by
19       using "-input" option.
20
21       The audio format is 16 bit, 1 channel, in Microsoft WAV format. If the
22       given filename already exists, it will be overridden.
23
24       If filename is "-" , the captured data will be streamed into standard
25       out, with no header (raw format).
26

OPTIONS

28       adinrec uses JuliusLib and adopts Julius options. Below is a list of
29       valid options.
30
31   adinrec specific options
32        -freq  Hz
33           Set sampling rate in Hz. (default: 16,000)
34
35        -raw
36           Output in raw file format.
37
38   JuliusLib options
39        -input  {mic|rawfile|adinnet|stdin|netaudio|esd|alsa|oss}
40           Choose speech input source. Specify 'file' or 'rawfile' for
41           waveform file. On file input, users will be prompted to enter the
42           file name from stdin.
43
44           'mic' is to get audio input from a default live microphone device,
45           and 'adinnet' means receiving waveform data via tcpip network from
46           an adinnet client. 'netaudio' is from DatLink/NetAudio input, and
47           'stdin' means data input from standard input.
48
49           At Linux, you can choose API at run time by specifying alsa, oss
50           and esd.
51
52        -lv  thres
53           Level threshold for speech input detection. Values should be in
54           range from 0 to 32767. (default: 2000)
55
56        -zc  thres
57           Zero crossing threshold per second. Only input that goes over the
58           level threshold (-lv) will be counted. (default: 60)
59
60        -headmargin  msec
61           Silence margin at the start of speech segment in milliseconds.
62           (default: 300)
63
64        -tailmargin  msec
65           Silence margin at the end of speech segment in milliseconds.
66           (default: 400)
67
68        -zmean
69           This option enables DC offset removal.
70
71        -smpFreq  Hz
72           Set sampling rate in Hz. (default: 16,000)
73
74        -48
75           Record input with 48kHz sampling, and down-sample it to 16kHz
76           on-the-fly. This option is valid for 16kHz model only. The
77           down-sampling routine was ported from sptk. (Rev. 4.0)
78
79        -NA  devicename
80           Host name for DatLink server input (-input netaudio).
81
82        -adport  port_number
83           With -input adinnet, specify adinnet port number to listen.
84           (default: 5530)
85
86        -nostrip
87           Julius by default removes successive zero samples in input speech
88           data. This option stop it.
89
90        -C  jconffile
91           Load a jconf file at here. The content of the jconffile will be
92           expanded at this point.
93
94        -plugindir  dirlist
95           Specify which directories to load plugin. If several direcotries
96           exist, specify them by colon-separated list.
97

ENVIRONMENT VARIABLES

99        ALSADEV
100           Device name string for ALSA. (default: "default")
101
102        AUDIODEV
103           Device name string for OSS. (default: "/dev/dsp")
104
105        PORTAUDIO_DEV
106           (portaudio V19) specify the name of capture device to use. See the
107           instruction output of log at start up how to specify it.
108
109        LATENCY_MSEC
110           Input latency of microphone input in milliseconds. Smaller value
111           will shorten latency but sometimes make process unstable. Default
112           value will depend on the running OS.
113

SEE ALSO

115        julius ( 1 ) ,
116        adintool ( 1 )
117

119       Copyright (c) 1991-2013 Kawahara Lab., Kyoto University
120
121       Copyright (c) 1997-2000 Information-technology Promotion Agency, Japan
122
123       Copyright (c) 2000-2005 Shikano Lab., Nara Institute of Science and
124       Technology
125
126       Copyright (c) 2005-2013 Julius project team, Nagoya Institute of
127       Technology
128

LICENSE

130       The same as Julius.
131
132
133
134                                  12/19/2013                        ADINREC(1)
Impressum